Search

This article explores the application of image processing techniques in recyclable waste paper sorting. In recycling, waste papers are segregated into various grades as they are subjected to different recycling processes. Highly sorted paper streams facilitate high quality end products and save processing chemicals and energy. From 1932 to 2009, different mechanical and optical paper sorting methods have been developed to fill the paper sorting demand. Still, in many countries including Malaysia, waste papers are sorted into different grades using a manual sorting system. Because of inadequate throughput and some major drawbacks of mechanical paper sorting systems, the popularity of optical paper sorting systems has increased. Automated paper sorting systems offer significant advantages over human inspection in terms of worker fatigue, throughput, speed, and accuracy. This research attempts to develop a smart vision sensing system that is able to separate the different grades of paper using first-order features. To construct a template database, a statistical approach with intra-class and inter-class variation techniques are applied to the feature selection process. Finally, the K-nearest neighbor (KNN) algorithm is applied for paper object grade identification. The remarkable achievement obtained with the method is the accurate identification and dynamic sorting of all grades of papers using simple image processing techniques.

Feature selection determines relevant features in the data. It is often applied in pattern classification, data mining, as well as machine learning. A special concern for feature selection nowadays is that the size of a database is normally very large, both vertically and horizontally. In addition, feature sets may grow as the data collection process continues. Effective solutions are needed to accommodate the practical demands. This paper concentrates on three issues: large number of features, large data size, and expanding feature set. For the first issue, we suggest a probabilistic algorithm to select features. For the second issue, we present a scalable probabilistic algorithm that expedites feature selection further and can scale up without sacrificing the quality of selected features. For the third issue, we propose an incremental algorithm that adapts to the newly extended feature set and captures `concept drifts' by removing features from previously selected and newly added ones. We expect that research on scalable feature selection will be extended to distributed and parallel computing and have impact on applications of data mining and machine learning.

Classification of text based on its substance is an essential part of analysis to organize enormously large text data and to mine the salient information contained in it. It is gaining greater attention with the surge in the volume of on-line data available. Classical algorithms like k-NN (k-nearest neighbor), SVM (Support Vector Machine) and their variations have been observed to yield only reasonable results in addressing the problem, leaving enough room for further improvement. A class of algorithms commonly referred to as Sparse Methods has been emerged recently from compressive sensing and found numerous effective applications in many areas of data analysis and image processing. Sparse Methods as a tool for text analysis is an alley that is largely unexplored rigorously. This paper presents exploration of sparse representation-based methods for text classification. Based on the success of sparse representation based methods in different areas of data analysis, we intuitively hypothesized that it should work well on text classification problems as well. This paper empirically reinforces the hypothesis by testing the method on Reuters and WebKB data sets. The empirical results on Reuters and WebKB benchmark data show that it can outperform classical classification algorithms like SVM and k-NN. It has been observed that obtaining the basis of representation and sparse codes are computationally costly operations affecting the performance of the system. We also propose a class-wise dictionary refinement algorithm and dynamic dictionary selection algorithm to make sparse coding faster. The addition of dictionary refinement to the classification system not only reduces the time taken for sparse coding but also gives improved classification accuracy. The outcomes of the study are empirical verification of sparse representation classifier as a text classification tool and a computationally efficient solution for the bottleneck operation of sparse coding.

Predictive analytics is an essential capability in business process management to forecast future status and performance of business processes. In this paper, we focus on one particular predictive monitoring task that is solved using classification techniques, i.e. predicting the next event in a case. Several different classifiers have been recently employed in the literature in this task. However, a quantitative benchmark of different classifiers is currently lacking. In this paper, we build such a benchmark by taking into account 20 classifiers from five families, i.e. trees, Bayesian, rule-based, neural and meta classifiers. We employ six real-world process event logs and consider two different sampling approaches, i.e. case and event-based sampling, and three different validation methods in order to acquire a comprehensive evaluation about the classifiers’ performance. According to our benchmark, the classifier most likely to be the overall superior performer is the credal decision tree (C-DT), followed by the other top-4 performers, i.e. random forest, decision tree, dagging ensemble, and nested dichotomies ensemble. We also provide a qualitative discussion of how features of an event log can affect the choice of best classifier.

People with type 1 diabetes must control their blood glucose level through insulin infusion either with several daily injections or with an insulin pump. However, estimating the required insulin dose is not easy. Recommender systems, mainly based on Case-Based Reasoning (CBR), are being developed to provide recommendations to users. These systems are designed to keep the experiences or cases of the user in a case-base, which requires maintenance to keep system's response accurate and efficient. This paper proposes a case-base maintenance methodology that combines case-base redundancy reduction and attribute weight learning. Contrary to previous approaches designed for classification problems, the maintenance methodology presented in this paper deals with numerical recommendations. It can manage a potentially huge case-base due to the combinatorial derived from the number of attributes used to represent a case. The proposed approach has been tested using the UVA/PADOVA type 1 diabetes simulator and the results demonstrate that it can accomplish better levels of accuracy than other insulin recommender systems mentioned in the literature, when a large number of attributes is considered This project has received funding from the European Union Horizon 2020 research and innovation programme under grant agreement No. 689810, www.pepper.eu.com/, PEPPER, and the grant of the University of Girona 20162018 (MPCUdG2016). The work has been developed with the support of the research group SITES awarded with distinction by the Generalitat de Catalunya (SGR 20142016)

Cross purchase modeling (cross model) is a method to simultaneously analyze multiple product categories for their interrelated influences on consumers’ decisions to purchase each category. Traditional econometric modeling methods are hard to compute and complex in model specifications. This paper examines an artificial neural network (ANN) approach in this context. To understand ANN models’ performance in increasing data scale, this paper uses four datasets of 4, 8, 16 and 32 categories to train ANN models and make predictions. Results show that an ANN model of 12 hidden nodes can be trained in about 3 h and make 88% prediction hit rate for the 16-category dataset. In contrast, a traditional econometric model requires more than 300 h to finish computing for the 16-category dataset. A typical critique of ANN technique is that it hides learned knowledge inside its model structure. This is a major obstacle preventing ANN from being more frequently applied in business research and practices. The current study takes two approaches to address this issue, i.e., (1) customizing ANN components to allow prior knowledge plugging in, and (2) using the generalized weight technique to reveal knowledge that is embedded in ANN training results. Findings of this paper help managers understand applicability of ANN technique in cross purchase model. By demonstrating plugging in prior knowledge to ANN model training and extracting knowledge from ANN training results, this paper shows approaches for understanding ANN embedded knowledge.

To assess the current mental state of an individual, several monitoring systems have been developed. In this paper, we explore the possibility to exploit information recorded noninvasively from the human cortex to develop a brain-computer interface (BCI) able to estimate brain workload and the mental efforts during a cognitive task. The EEG-based workload classifier presented in this paper combines a power spectral density (PSD) analysis and a statistical criterion. The proposed classifier is applied in the context of distance education and online course platform through two experimental protocols. The first one proposes solving a set of matrices products using pen and paper, while the second one proposes answering problems of logic mathematics on a computer-based learning environment. Experimental results show that the averaged accuracy of distinguishing changes in the theta [4–7 Hz] (θ) band is 79%. For the alpha band [8–11 Hz] (α) the averaged accuracy reached 78%. Based on this classifier, we demonstrate that θ and α powers in central, and posterior sites decrease with the increase in difficulty level of the cognitive task. The accuracy of correct decisions obtained from our results are significantly enhanced while comparing our investigation to some similar works from literature. In the realm of intelligent expert systems, our work results represent a first step to an implementation of an intelligent system for the evaluation of reeducative therapies to be used in physiotherapy centers for children with cognitive disorders as it is the case for Cerebral Palsy.

This study evaluates the performance of different data clustering approaches for searching the profitable consumer segments in the UK hospitality industry. The paper focuses on three aspects of datasets including the ordinal nature of data, high dimensionality and outliers. Data collected from 513 sample points are analysed in this paper using four clustering approaches: Hierarchical clustering, K-Medoids, fuzzy clustering, and Self-Organising Maps (SOM). The findings suggest that Fuzzy and SOM based clustering techniques are comparatively more efficient than traditional approaches in revealing the hidden structure in the data set. The segments derived from SOM has more capability to provide interesting insights for data-driven decision making in practice. This study makes a significant contribution to literature by comparing different clustering approaches and addressing misconceptions of using these for market segmentation to support data-driven decision making in business practices.

In this paper we apply a series of Machine Learning models to a recently published unique dataset on the mortality of COVID19 patients. We use a dataset consisting of blood samples of 375 patients admitted to a hospital in the region of Wuhan, China. There are 201 patients who survived hospitalisation and 174 patients who died whilst in hospital. The focus of the paper is not only on seeing which Machine Learning model is able to obtain the absolute highest accuracy but more on the interpretation of what the Machine Learning models provides. We find that age, days in hospital, Lymphocyte and Neutrophils are important and robust predictors when predicting a patients mortality. Furthermore, the algorithms we use allows us to observe the marginal impact of each variable on a case-by-case patient level, which might help practicioneers to easily detect anomalous patterns. This paper analyses the global and local interpretation of the Machine Learning models on patients with COVID19.

Lithology identification is an important part of petroleum drilling engineering. Accurate identification of lithology is the foundation to ensure the smooth operation of drilling engineering. Conventional lithology recognition mainly relies on human experience. The recognition accuracy depends on the level of technical personnel and the recognition response time is lagging. It is difficult to meet the demand. How to achieve rapid and intelligent recognition of lithology is one of the core technical problems faced by oil drilling. In order to solve this problem, this paper uses the mechanical specific energy and other ground parameters to establish a rapid and intelligent recognition method of lithology based on the simulated annealing optimization support vector machine model. In order to improve the accuracy of the model recognition, a large number of methods have been developed from two classes and multiple classes, simulation analysis results show that the lithology recognition model based on the principle of mechanical specific energy and the simulated annealing optimization support vector machine algorithm can predict a priori unknown data with a prediction accuracy of over 90%. Compared with the support vector machine model and the K-means model, simulated annealing optimization support vector machine is used for comparative analysis, the algorithm to establish a lithology recognition model has better performance and higher accuracy. The intelligent identification model of lithology based on the principle of mechanical specific energy and simulated annealing optimization support vector machine algorithm established in this paper can quickly and accurately identify lithology, and provide new technical support for oil drilling formation analysis.

Over the last few years, we have been witnessing a dramatic progress of deep learning in many real world applications. Deep learning concepts have been originated in the area of neural network and show a quantum leap in effective feature learning techniques such as auto-encoders, convolutional neural networks, recurrent neural networks etc. In the case of kernel machines, there are several attempts to model learning machines that mimic deep neural networks. In this direction, Multilayer Kernel Machines (MKMs) was an attempt to build a kernel machine architecture with multiple layers of feature extraction. It composed of many layers of kernel PCA based feature extraction units with support vector machine having arc-cosine kernel as the final classifier. The other approaches like Multiple Kernel Learning (MKL) and deep core vector machines solve the fixed kernel computation problem and scalability aspects of MKMs respectively. In addition to this, there are lot of avenues where the use of unsupervised MKL with both single and multilayer kernels in the multilayer feature extraction framework have to be evaluated. In this context, this paper attempts to build a scalable deep kernel machines with multiple layers of feature extraction. Each kernel PCA based feature extraction layer in this framework is modeled by the combination of both single and multilayer kernels in an unsupervised manner. Core vector machine with arc-cosine kernel is used as the final layer classifier which ensure the scalability in this model. The major contribution of this paper is a novel effort to build a deep structured kernel machine architecture similar to deep neural network architecture for classification. It opens up an extendable research avenue for researchers in deep learning based intelligent system leveraging the principles of kernel theory. Experiments show that the proposed method consistently improves the generalization performances of existing deep core vector machine.

DBN- based classification model is proposed in this paper for web spam detection.SMOTE and DAE algorithms is applied in DBN to improve the classification performanceThe content and link feature is combined.The results obtained in this paper is better than the existing systems. With the development of the Internet, the number of web spam increases gradually, which has seriously affected the user experience of search engines. To improve the classification performance of web spam, the deep belief networks (DBN) is used for the first time, and it is effectively combined with the Synthetic Minority Over-Sampling Technique (SMOTE) and De-Noising Auto-Encoder (DAE) algorithm after the multi-aspect research and consideration. After multiple sets of experiments on WEBSPAM-UK2007 dataset, the results show that the classification method proposed in this paper improves the classification performance to a certain extent, which provides a good direction for the future classification of web spam.

The research and practice of information systems have progressed by leaps and bounds due to the emergence of big data analytics and machine learning. The paper undertakes a bibliometric study to analyze the contributions of major authors, universities/organizations, and countries in terms of productivity, citations, and bibliographic coupling. A sample of 2160 articles from the Scopus for the period 2006–2020 is the basis of the study. The publications are grouped into five clusters, of which Cluster 1 is consistently dominant in the information systems publication landscape. Cluster 2 includes published studies on the Internet of Things, security, and cloud computing, which have also been widely researched. Cluster 3, the third-largest cluster, has attempted to investigate social media analytics. Cluster 4 aims to look into the impact of classification and predictive, which is found to have sustained research interest. Topics with scant coverage in terms of papers are primarily in Cluster 5, indicating saturation in the area and the need for conducting inter-disciplinary studies. The results of our study provide valuable insights for potential contributors and global audiences in terms of emerging topics for research.

This short communication provides a discourse emerged after reading “Stacking ensemble based deep neural networks modeling for effective epileptic seizure detection, Expert Systems with Applications, 148, 113239, 2020.” The discussed paper proposes a novel application of stacking-based ensemble for seizure detection, where several deep neural networks were used as base classifiers. The ensemble design and experimental results presented by the author show some weaknesses, which is indicated by, one of which, an inability of the proposed model to outperform previous studies. In this note, controversy of the discussed paper is explained and an improved version of stacking-based deep neural network is also further introduced and detailed to prevent it in the future.

Music radio data is currently underutilised in radio program management. Software tools that listen to and analyse music airplay are in many markets nonexistent, limited, or unaffordable. In this paper we present a novel knowledge discovery and visualisation framework for broadcast radio, ZeitMetric. The ZeitMetric framework uses machine learning and music information retrieval techniques to label radio audio automatically for knowledge discovery. The framework incorporates a novel music dataset collection technique (MusiGrab) to leverage online music services for ground-truth data, as well as a novel knowledge visualisation and presentation technique based on self-organizing maps (ZeitViz). The framework is compared to what little literature relating to this topic exists, and a set of requirements for a high-quality broadcast radio knowledge discovery is developed. MusiGrab specifically is compared to an existing static music information retrieval dataset and shown to offer superior results in this context. Future research directions using and extending the framework are also discussed. On acceptance of the paper, code for a use-case of the MusiGrab dataset collection technique will be released on GitHub.

The variety and plethora of research papers available on the Web motivated researchers to propose models that could assist users with personalized citation recommendations. In recent years, citation recommendation models using Network Representation Learning (NRL) methods have shown promising results. Nevertheless, existing NRL-based models are limited in terms of exploiting semantic relations and contextual information between the objects of bibliographic papers’ networks. Additionally, these models cannot adequately explore the structure of heterogeneous information networks, topical relevance, and relevant semantics. Consequently, they suffer from network sparsity and inadequate personalization problems. To overcome these shortcomings, we present a network embedding model termed as Global Citation Recommendation employing Generative Adversarial Network (GCR-GAN). The proposed model exploits the Heterogeneous Bibliographic Network (HBN) to generate personalized citation recommendations. In particular, the proposed model utilizes semantic relations corresponding to the objects of the heterogeneous bibliographic network and captures network structure proximity employing the Scientific Paper Embeddings using Citation-informed Transformers (SPECTER) and Denoising Auto-encoder networks to learn semantic-preserving graph representations. Compared to baseline models, the recommendations generated by our model over the DBLP and ACM datasets prove that it outperforms baseline methods by gaining almost 11% and 12% improvement in terms of Mean Average Precision (MAP) and Normalized Discounted Cumulative Gain (nDCG) metrics, respectively. Furthermore, we analyzed the effectiveness of the proposed model considering network sparsity issue, where our model gains almost 7% better recall@100 score against the second-best counterpart.

Crowdsourcing as an important computing resource for the Crowd-based Cooperative, crowdsourcing workers, due to the complexity of their personnel composition and the ambiguity of group characteristics, make it difficult to accurately recommend suitable worker groups for the task. Recommending crowdsourcing tasks to suitable workers can greatly improve the efficiency and quality of the execution of crowdsourcing tasks. The current crowdsourcing recommendation algorithm is based on the single characteristics of the workers, ignoring the multi-dimensional characteristics of the workers and the community characteristics of the crowd. This paper proposes a worker group recommendation method based on multi-community collaboration (GRMBC) by utilizing the worker characteristics information extracted from crowdsourcing platform. Based on the characteristics of workers'reputation, preference and activity, the method divides the worker group into several characteristics communities with similar behavior to discover the potential multi-community structure in the crowdsourcing worker group, and then selects Top-N worker group for recommendation through the interaction among multi-communities. At the same time, we also proposed two mitigation strategies for the cold start problem of data in crowdsourcing. This paper uses the public data collected by AMT to do the experiments, and compares the aggregation results of the recommendations generated by different algorithms. The results show the recommendations generated by the GRBMC algorithm proposed in this paper performs the best comprehensively. When the GRBMC algorithm that considers both worker attributes and communi-ty characteristics has an accuracy improvement of 0.03 ~ 0.04 compared with not using the recommendation algorithm on each index, the accuracy of 0.01 ~ 0.02 is improved com-pared with the method considering single characteristic. Moreover, compared with the individual recommendation method of the workers, the recommendation method of the workers' group is more in line with the platform requirements, and can well reflect the wisdom of crowd wisdom.

This paper introduces a three-step framework for classifying multiclass radiography images. The first step utilizes a de-noising technique based on wavelet transform (WT) and the statistical Kolmogorov Smirnov (KS) test to remove noise and insignificant features of the images. An unsupervised deep belief network (DBN) is designed for learning the unlabelled features in the second step. Although small-scale DBNs have demonstrated significant potential, the computational cost of training the restricted Boltzmann machine is a major issue when scaling to large networks. Moreover, noise in radiography images can cause a significant corruption of information that hinders the performance of DBNs. The combination of WT and KS test in the first step helps improve performance of DBNs. Discriminative feature subsets obtained in the first two steps serve as inputs into classifiers in the third step for evaluations. Five frequently used classifiers including naive Bayes, radial basis function network, random forest, sequential minimal optimization, and support vector machine and four different case studies are implemented for experiments using the Image Retrieval in Medical Application data set. The experimental results show that the three-step framework has significantly reduced computational cost and yielded a great performance for multiclass radiography image classification. Along with effective applications in image processing in other fields published in the literature, deep learning network in this paper has again demonstrated its robustness in handling a complex set of medical images. This implies that the proposed approach can be implemented in real practice for analysing noisy radiography images, which have many useful medical applications such as diagnosis of diseases related to lung, breast, musculoskeletal or pediatric studies.

We propose estimating the quality of a contrast pattern using unseen objects.We evaluate quality measures by correlating their values and the estimated quality.We describe the influence of database characteristics in correlations.We perform a study to find how to synergistically combine quality measures. Contrast patterns, which lie in the core of most understandable classifiers, are frequently evaluated by quality measures. Since many different quality measures are available, they should be compared to select the most appropriate for each applications. This paper introduces a method to compare quality measures, using a set of mined patterns and a collection of objects not used for mining. The comparison is performed by correlating quality values with a quality estimation of the patterns. Additionally, a meta-learning study is performed to show that combining quality measures could be better than using the best single measures in isolation. The results of this paper can help researchers to create new quality measures or to find new combinations of quality measures to create better understandable classification systems.

Traditionally, the probably approximately correct (PAC) learning refers the single concept class. We discuss the PAC framework of the multiple tasks in the joint inference model. And we extend PAC learning to multi-concept classes.We present an ensemble learning approach to joint inference on the three NLP sub-tasks. We explain how to combine those weak learners to a strong ability and present the dynamic weighted combination method in the ensemble joint inference model.Our Ensemble Markov Logic Networks (EMLNs) address the problem of the Markov Logic Networks intractable dealing with the large scale data. Experiments show that this approach leads to a higher precision and recall than that of pipeline approaches. Joint inference is a fundamental issue in the field of artificial intelligence. The greatest advantage of the joint inference is demonstrated by its capability of avoiding errors from cascading and accumulating on a pipeline of multiple chained sub-tasks. Markov Logic Network(MLN) is the most common joint inference model that provides a flexible representation and handles uncertainty. It has been applied successfully to joint inference on many natural language processing tasks to avoid error propagation. However, due to the great expressiveness of first-order logic, the representation for it in MLN generates rather complicated graph structures, which makes the learning and inference on large scale data intractably. In this paper, we present an ensemble learning approach to deal with the challenges in MLNs. Firstly, we give a proof within the probably approximately correct (PAC) framework. The proof points out what conditions are necessary for successful applying the ensemble learning approach to MLN. Secondly, the paper explains how to combine the learners. Finally, in order to illustrate the working mechanism of the ensemble joint inference model, we present an Ensemble Markov Logic Networks (EMLNs) method and use it to extract knowledge from a large scale corpus published by Google.11code.google.com/p/relation-extraction-corpus/. Experiments suggest that significant speedup can be gained by the EMLNs. Meanwhile, it show that this approach leads to a higher precision and recall than that of those pipeline approaches.

Customer purchase prediction aims to predict customers' future purchases, and the prediction results are of great importance for conducting future commercial activities. To obtain accurate predictions of customer purchases, this paper develops a machine learning framework based on historical behavioural data. First, considering the sparsity of behavioural data, this paper proposes a feature combination method based on the improved factorization machine algorithm. Second, due to the imbalance of customer purchase data, this paper proposes an imbalanced prediction method based on the maximized marginal category and cost-sensitive ensemble learning. Finally, a real-word travel service purchase dataset is adopted to test the feasibility of the proposed prediction framework. The experimental results and comparative analysis verify the validity of the proposed model.

Priority rules are applied in many commercial software tools for scheduling projects under limited resources because of their known advantages such as the ease of implementation, their intuitive working, and their fast speed. Moreover, while numerous research papers present comparison studies between different priority rules, managers often do not know which rules should be used for their specific project, and therefore have no other choice than selecting a priority rule at random and hope for the best. This paper introduces a decision tree approach to classify and detect the best performing priority rule for the resource-constrained project scheduling problem (RCPSP). The research relies on two classification models to map project indicators onto the performance of the priority rule. Using such models, the performance of each priority rule can be predicted, and these predictions are then used to automatically select the best performing priority rule for a specific project with known network and resource indicator values. A set of computational experiment is set up to evaluate the performance of the newly proposed classification models using the most well-known priority rules from the literature. The experiments compare the performance of multi-label classification models with multi-class classification models, and show that these models can outperform the average performance of using any single priority rule. It will be argued that this approach can be easily extended to any extension of the RCPSP without changing the methodology used in this study. info:eu-repo/semantics/publishedVersion

This paper presents a systematic procedure to fairly compare experimental performance scores for machine learning methods for fault diagnosis based on vibration signals. In the vast majority of related scientific publications, the estimated accuracy and similar performance criteria are the sole quality parameter presented. However, the experimental design giving rise to these results is mostly biased, based on unacceptably simple validation methods and on recycling identical patterns in test data sets, previously used for training. Moreover, the methods in general overfit their hyperparameters, introducing additional overoptimistic results. In order to remedy this defect, we critically analyse the usual training-validation-test division and propose an algorithmic guideline in the form of a validation framework. This allows a well defined comparison of experimental results. In order to illustrate the ideas of the paper, the Case Western Reserve University Bearing Data benchmark is used as a case study. Four distinct classifiers are experimentally compared, under gradually more difficult generalization tasks using the proposed evaluation framework: K-Nearest-Neighbor, Support Vector Machine, Random Forest and One-Dimensional Convolutional Neural Network. An extensive literature review suggests that most vibration based research papers, particularly for the Case Western Reserve University Bearing Data, use similar patterns for training and testing, making their classification an easy task.

From unsupervised to supervised learning a fault detection model (for robots).Insights to why and when it becomes more accurate.Theoretical analysis and a prediction tool.Empirical results on 3 real-world domains that back these insights. The use of robots in our daily lives is increasing. As we rely more on robots, thus it becomes more important for us that the robots will continue on with their mission successfully. Unfortunately, these sophisticated, and sometimes very expensive, machines are susceptible to different kinds of faults. It becomes important to apply a Fault Detection (FD) mechanism which is suitable for the domain of robots. Two important requirements of such a mechanism are: high accuracy and low computational-load during operation (online). Supervised learning can potentially produce very accurate FD models, and if the learning takes place offline then the online computational-load can be reduced. Yet, the domain of robots is characterized with the absence of labeled data (e.g., faulty, normal) required by supervised approaches, and consequently, unsupervised approaches are being used. In this paper we propose a hybrid approach - an unsupervised approach can label a data set, with a low degree of inaccuracy, and then the labeled data set is used offline by a supervised approach to produce an online FD model. Now, we are faced with a choice should we use the unsupervised or the hybrid fault detector? Seemingly, there is no way to validate the choice due to the absence of (a priori) labeled data. In this paper we give an insight to why, and a tool to predict when, the hybrid approach is more accurate. In particular, the main impacts of our work are (1) we theoretically analyze the conditions under which the hybrid approach is expected to be more accurate. (2) Our theoretical findings are backed with empirical analysis. We use data sets of three different robotic domains: a high fidelity flight simulator, a laboratory robot, and a commercial Unmanned Arial Vehicle (UAV). (3) We analyze how different unsupervised FD approaches are improved by the hybrid technique and (4) how well this improvement fits our prediction tool. The significance of the hybrid approach and the prediction tool is the potential benefit to expert and intelligent systems in which labeled data is absent or expensive to create.

A taxonomy that classifies ensemble models in the literature is presented.Surface and deep features integration is explored to improve classification.Several ensembles of classifiers and features are proposed and evaluated.Performance of the proposed models is evaluated on several sentiment datasets. Deep learning techniques for Sentiment Analysis have become very popular. They provide automatic feature extraction and both richer representation capabilities and better performance than traditional feature based techniques (i.e., surface methods). Traditional surface approaches are based on complex manually extracted features, and this extraction process is a fundamental question in feature driven methods. These long-established approaches can yield strong baselines, and their predictive capabilities can be used in conjunction with the arising deep learning methods. In this paper we seek to improve the performance of deep learning techniques integrating them with traditional surface approaches based on manually extracted features. The contributions of this paper are sixfold. First, we develop a deep learning based sentiment classifier using a word embeddings model and a linear machine learning algorithm. This classifier serves as a baseline to compare to subsequent results. Second, we propose two ensemble techniques which aggregate our baseline classifier with other surface classifiers widely used in Sentiment Analysis. Third, we also propose two models for combining both surface and deep features to merge information from several sources. Fourth, we introduce a taxonomy for classifying the different models found in the literature, as well as the ones we propose. Fifth, we conduct several experiments to compare the performance of these models with the deep learning baseline. For this, we use seven public datasets that were extracted from the microblogging and movie reviews domain. Finally, as a result, a statistical study confirms that the performance of these proposed models surpasses that of our original baseline on F1-Score.

A theorem characterizing the property of the optimal solution is presented.A hybrid evolutionary algorithm (HEA) is proposed.Extreme machine learning is used to approximate the fitness of most individuals.Two heuristics are incorporated to generate a good initial population.The proposed algorithm is computationally effective. This paper considers the two-stage capacitated facility location problem (TSCFLP) in which products manufactured in plants are delivered to customers via storage depots. Customer demands are satisfied subject to limited plant production and limited depot storage capacity. The objective is to determine the locations of plants and depots in order to minimize the total cost including the fixed cost and transportation cost. However, the problem is known to be NP-hard. A practicable exact algorithm is impossible to be developed. In order to solve large-sized problems encountered in the practical decision process, an efficient alternative approximate method becomes more valuable. This paper aims to propose a hybrid evolutionary algorithm framework with machine learning fitness approximation for delivering better solutions in a reasonable amount of computational time. In our study, genetic operators are adopted to perform the search process and a local search strategy is used to refine the best solution found in the population. To avoid the expensive consumption of computational time during the fitness evaluating process, the framework uses extreme machine learning to approximate the fitness of most individuals. Moreover, two heuristics based on the characteristics of the problem is incorporated to generate a good initial population. Computational experiments are performed on two sets of test instances from the recent literature. The performance of the proposed algorithm is evaluated and analyzed. Compared with other algorithms in the literature, the proposed algorithm can find the optimal or near-optimal solutions in a reasonable amount of computational time. By employing the proposed algorithm, facilities can be positioned more efficiently, which means the fixed cost and the transportation cost can be decreased significantly, and organizations can enhance competitiveness by using the optimized facility location scheme.

Automatic generation of user interfaces from domain knowledge: ARBUI.Practical implementation of the proposed architecture (ARBUI): the Semantic MVC.Tested our approach in a pilot project at the Oncology Center in Warsaw. Motivation: The ability to directly trace how requirements are implemented in a software system is crucial in domains that require a high level of trust (e.g. medicine, law, crisis management). This paper describes an approach that allows a high level of traceability to be achieved with model-driven engineering supported by automated reasoning. The paper gives an introduction to the novel, automated user interface synthesis in which a set of requirements is automatically translated into a working application. It is presented as a generalization of the current state of the art model-driven approaches both from the conceptual perspective as well as the concrete implementation is discussed together with its advantages like the alignment of business logic with the application and ease of adaptability. It also presents how a high level of traceability can be obtained if runtime support of automated reasoning over models is applied.Results: We have defined the Automated Reasoning-Based User Interface (ARBUI) approach and implemented a framework for application programming that follows our definition. The framework, called Semantic MVC, is based on model-driven engineering principles enhanced with W3C standards for the semantic web. We will present the general architecture and main ideas underlying our approach and framework. Finally, we will present a practical application of the Semantic MVC that we created in the medical domain as a Clinical Decision Support System for GIST cancer in cooperation with the Maria Sklodowska-Curie Memorial Cancer Center and Institute of Oncology in Warsaw. The discussed expert system allows the expert to directly modify the executable knowledge on the fly, making the overall system cost effective.

Novel fuzzy rule-based system (FRBS) for medical data classification tasks is proposed.FRBSs are designed using multi-objective evolutionary optimization algorithms.Set of FRBSs with various levels of accuracy-interpretability trade-off is generated.Benchmark medical data sets are used to evaluate the effectiveness of the system.Highly interpretable and accurate medical decision support is provided by our approach. In medical decision support systems, both the accuracy (i.e., the ability to adequately represent the decision making processes) as well as the transparency and interpretability (i.e., the ability to provide a domain user with compact and understandable explanation and justification of the proposed decisions) play essential roles. This paper presents an approach for automatic design of fuzzy rule-based classification systems (FRBCSs) from medical data using multi-objective evolutionary optimization algorithms (MOEOAs). Our approach generates, in a single run, a collection of solutions (medical FRBCSs) characterized by various levels of accuracy-interpretability trade-off. We propose a new complexity-related interpretability measure and we address the semantics-related interpretability issue by means of efficient implementation of the so-called strong fuzzy partitions of attribute domains. We also introduce a special-coding-free representation of the rule base and original genetic operators for its processing as well as we implement our ideas in the context of well-known and one of the presently most advanced MOEOAs, i.e., Non-dominated Sorting Genetic Algorithm II (NSGA-II). An important part of the paper is devoted to a broad comparative analysis of our approach and as many as 26 alternative techniques arranged in 32 experimental set-ups and applied to three well-known benchmark medical data sets (Breast Cancer Wisconsin (Original), Pima Indians Diabetes, and Heart Disease (Cleveland)) available from the UCI repository of machine learning databases (http://archive.ics.uci.edu/ml). A number of useful in medical applications performance measures including accuracy, sensitivity, specificity, and several interpretability measures are employed. The results of such a broad comparative analysis demonstrate that our approach significantly outperforms the alternative methods in terms of the interpretability of the obtained FRBCSs while remaining either competitive or superior in terms of their accuracy. It is worth stressing that the overwhelming majority of the existing medical classification methods concentrate almost exclusively on the accuracy issues.

Random forests are grown on convolutional neural networks for scene categorization.Features from multi-layers of deep convolutional neural networks are utilized.A feature selection method is proposed to use random forests to categorize scenes. Breakthrough performances have been achieved in computer vision by utilizing deep neural networks. In this paper we propose to use random forest to classify image representations obtained by concatenating multiple layers of learned features of deep convolutional neural networks for scene classification. Specifically, we first use deep convolutional neural networks pre-trained on the large-scale image database Places to extract features from scene images. Then, we concatenate multiple layers of features of the deep neural networks as image representations. After that, we use random forest as the classifier for scene classification. Moreover, to reduce feature redundancy in image representations we derived a novel feature selection method for selecting features that are suitable for random forest classification. Extensive experiments are conducted on two benchmark datasets, i.e. MIT-Indoor and UIUC-Sports. Obtained results demonstrated the effectiveness of the proposed method. The contributions of the paper are as follows. First, by extracting multiple layers of deep neural networks, we can explore more information of image contents for determining their categories. Second, we proposed a novel feature selection method that can be used to reduce redundancy in features obtained by deep neural networks for classification based on random forest. In particular, since deep learning methods can be used to augment expert systems by having the systems essentially training themselves, and the proposed framework is general, which can be easily extended to other intelligent systems that utilize deep learning methods, the proposed method provide a potential way for improving performances of other expert and intelligent systems.

Focus is on computational intelligence methods in prostate cancer predictive modeling.We survey metaheuristic optimisation methods.We review machine learning methods.We consider cancer data of different modalities.We discuss recent advances, challenges and provide future directions. Predictive modeling in medicine involves the development of computational models which are capable of analysing large amounts of data in order to predict healthcare outcomes for individual patients. Computational intelligence approaches are suitable when the data to be modelled are too complex for conventional statistical techniques to process quickly and efficiently. These advanced approaches are based on mathematical models that have been especially developed for dealing with the uncertainty and imprecision which is typically found in clinical and biological datasets. This paper provides a survey of recent work on computational intelligence approaches that have been applied to prostate cancer predictive modeling, and considers the challenges which need to be addressed. In particular, the paper considers a broad definition of computational intelligence which includes metaheuristic optimisation algorithms (also known as nature inspired algorithms), Artificial Neural Networks, Deep Learning, Fuzzy based approaches, and hybrids of these, as well as Bayesian based approaches, and Markov models. Metaheuristic optimisation approaches, such as the Ant Colony Optimisation, Particle Swarm Optimisation, and Artificial Immune Network have been utilised for optimising the performance of prostate cancer predictive models, and the suitability of these approaches are discussed.

Four methods are developed for data mining discrete multi-objective optimization datasets.Two of the methods are unsupervised, one is supervised and the other is hybrid.Knowledge is represented as patterns in one method, and as rules in other methods.Methods are applied to three real-world production system optimization problems.Extracted knowledge is compared across methods and provides new insights. The first part of this paper served as a comprehensive survey of data mining methods that have been used to extract knowledge from solutions generated during multi-objective optimization. The current paper addresses three major shortcomings of existing methods, namely, lack of interactiveness in the objective space, inability to handle discrete variables and inability to generate explicit knowledge. Four data mining methods are developed that can discover knowledge in the decision space and visualize it in the objective space. These methods are (i) sequential pattern mining, (ii) clustering-based classification trees, (iii) hybrid learning, and (iv) flexible pattern mining. Each method uses a unique learning strategy to generate explicit knowledge in the form of patterns, decision rules and unsupervised rules. The methods are also capable of taking the decision makers preferences into account to generate knowledge unique to preferred regions of the objective space. Three realistic production systems involving different types of discrete variables are chosen as application studies. A multi-objective optimization problem is formulated for each system and solved using NSGA-II to generate the optimization datasets. Next, all four methods are applied to each dataset. In each application, the methods discover similar knowledge for specified regions of the objective space. Overall, the unsupervised rules generated by flexible pattern mining are found to be the most consistent, whereas the supervised rules from classification trees are the most sensitive to user-preferences.

In this research UCI Indian Liver Patient Dataset (ILPD) used.Boosted C5.0 and CHAID algorithms are used to identify liver disease risk factors.This research shows females have more chance of liver disease than males.Common risk factors of liver disease were extracted by data mining.This research produced quite simple rules. The human liver is one of the major organs in the body and liver disease can cause many problems in human life. Fast and accurate prediction of liver disease allows early and effective treatments. In this regard, various data mining techniques help in better prediction of this disease. Because of the importance of liver disease and increase the number of people who suffer from this disease, we studied on liver disease through using two well-known methods in data mining area.In this paper, novel decision tree based algorithms is used which leads to considering more factors in general and predictions with high accuracy compared to other studies in liver disease. In this application, 583 UCI instances of liver disease dataset from the UCI repository are considered. This dataset consists of 416 records of liver disease and 167 records of healthy liver. This dataset is analyzed by two algorithms named Boosted C5.0 and CHAID algorithms. Until now there is no work in the literature that uses boosted C5.0 and CHAID for creating the rules in liver disease. Our results show that in both algorithms, the DB, ALB, SGPT, TB and A/G factors have a significant impact on predicting liver disease which according to the rules generated by both algorithms important ranges are DB=10.900-1.200, ALB 4.00-4.300, SGPT=34-37, TB=0.600-1.200 (by boosted C5.0), A/G=1.180-1.390, as well as in the Boosted C5.0 algorithm, Alkphos, SGOT and Age have significant impact in prediction of liver disease. By comparing the performance of these algorithms, it becomes clear that C5.0 algorithm via Boosting technique has an accuracy of 93.75% and this result reveals that it has a better performance than the CHAID algorithm which is 65.00%. Another important achievement of this paper is about the ability of both algorithms to produce rules in one class for liver disease. The results of our assessment show that Boosted C5.0 and CHAID algorithms are capable to produce rules for liver disease. Our results also show that boosted C5.0 considers the gender in liver disease, a factor which is missing in many other studies. Meanwhile, using the rules generated in boosted C5.0 algorithm, we obtained the important result about low susceptibility of female to liver disease than male. This factor is missing in other studies of liver disease. Therefore, our proposed computer-aided diagnostic methods as an expert and intelligent system have impressive impact on liver disease detection. Based on obtained results, we observed that our model had better performance compared to existing methods in the literature.

User interactions are used to build contextual recommendation system.A Trace-Based Reasoning process is applied to retrieve and adapt similar episodes.An evaluation protocol measures the performance, accuracy and user satisfaction.Similarity measures are used to compare between interaction traces.The Scenario example is a specific video composition application called Wanaclip. Nowadays, many recent applications retain traces of their usage by collecting user information. These traces help to understand user behavior and activities thus reflect the context. This paper describes how interaction traces allow the building of contextual recommendations using a Trace-Based Reasoning approach. Trace-Based Reasoning is an artificial intelligence paradigm that draws its inspiration from Case-Based Reasoning. In TBR, modeled traces act as the main knowledge container. The application considered in this paper, Wanaclip, is an interactive online video clip composition application. We added a recommendation system that guides users in both video creation and selection. The recommendation engine is fueled by interaction traces provided by previous users and is stored in T Store, a Trace Base Management System that handles the storage, processing and exploitation of traces. This approach uses similarity measures for finding and comparing episodes of traces. We validate our approach by proposing a variation to the classical accuracy definition, which we call "acceptance rate". Our evaluations show that this approach offers satisfactory results in term of recommendations and response time.

The adaptive rule-based classifier is used to classify multi-class biological data.It applies random subspace and boosting approaches with ensemble of decision trees.Decision tree induction is used for evolving rules from the biological data.k-nearest-neighbor is used for removing ambiguity between the contradictory rules.The classifier is evaluated using 148 Exome data sets and 10 life sciences data sets. In this paper, we introduce a new adaptive rule-based classifier for multi-class classification of biological data, where several problems of classifying biological data are addressed: overfitting, noisy instances and class-imbalance data. It is well known that rules are interesting way for representing data in a human interpretable way. The proposed rule-based classifier combines the random subspace and boosting approaches with ensemble of decision trees to construct a set of classification rules without involving global optimisation. The classifier considers random subspace approach to avoid overfitting, boosting approach for classifying noisy instances and ensemble of decision trees to deal with class-imbalance problem. The classifier uses two popular classification techniques: decision tree and k-nearest-neighbor algorithms. Decision trees are used for evolving classification rules from the training data, while k-nearest-neighbor is used for analysing the misclassified instances and removing vagueness between the contradictory rules. It considers a series of k iterations to develop a set of classification rules from the training data and pays more attention to the misclassified instances in the next iteration by giving it a boosting flavour. This paper particularly focuses to come up with an optimal ensemble classifier that will help for improving the prediction accuracy of DNA variant identification and classification task. The performance of proposed classifier is tested with compared to well-approved existing machine learning and data mining algorithms on genomic data (148 Exome data sets) of Brugada syndrome and 10 real benchmark life sciences data sets from the UCI (University of California, Irvine) machine learning repository. The experimental results indicate that the proposed classifier has exemplary classification accuracy on different types of biological data. Overall, the proposed classifier offers good prediction accuracy to new DNA variants classification where noisy and misclassified variants are optimised to increase test performance.

An approach to bankruptcy forecasting and solution is proposed.The Case-Based Reasoning paradigm is used, focusing on Revise step.Different from the past, pure CBR has been applied in a real case study.Compared with Z"-Score, the method shows good performance in predicting bankruptcy.The approach suggests how to act before the firm situation becomes irreversible. Bankruptcy prediction is a very important research trend: although statistical methods are mainly used in literature, techniques based on Artificial Intelligence are interesting from many points of view. Among them, Case-Based Reasoning (CBR) could be useful to cluster enterprises according to opportune similarity metrics as well as suggest proper actions to take for avoiding bankruptcy in border-line situations. In this paper, we present a new and still under development CBR approach to this problem, that seems to return better results than previous attempts. The approach is based on different kinds of similarity metrics and is focused on the implementation of innovative revise algorithms. In particular, the paper shows how the revise step is crucial to improve the accuracy of the bankruptcy prediction model.

Adaptive learning rate has been proposed for Deep Learning in MLP.Technique for updating learning rate is free of hyper-parameters.Learning rate is a function of a parameter called learning parameter.Learning parameter is updated based on error gradient.Learning rate is further updated based on the Laplacian score of activation values. An attempt has been made to improve the performance of Deep Learning with Multilayer Perceptron (MLP). Tuning the learning rate or finding an optimum learning rate in MLP is a major challenge. Depending on the value of the learning rate, classification accuracy can vary drastically. This issue has been taken as a challenge in this paper. In this paper, a new approach has been proposed to combine adaptive learning rate in conjunction with the concept of Laplacian score for varying the weights. Learning rate is taken as a function of parameter which itself is updated on the basis of error gradient by forming mini-batches. Laplacian score of the neuron isfurther used for updating the incoming weights. This removes the bottleneck involved in finding the optimum value for the learning rate in Deep Learning by using MLP. It is observed on benchmark datasets that this approach leads to increase in classification accuracy as compared to the existing benchmark levels achieved by the well known methods of deep learning.

We describe method for purifying category structure of Wikipedia.We propose three methods for identification of associations between categories using SVM.Evaluation indicates the methods allows us to identify new significant relations.The aggregated results have been used for visualization of Wikipedia categories. Description of the data using categories allows one to describe it on a higher abstraction level. In this way, we can operate on aggregated groups of the information, allowing one to see relationships that do not appear explicit when we analyze the individual objects separately. In this paper we present automatic identification of the associations between categories used for organization of the textual data. As experimental data we used a network of English Wikipedia articles and their associated categories, that have been preprocessed by a dedicated filtering method for noise reduction. The main contribution of the paper is the introduction of the method based on supervised machine learning for mining relations between these categories. We describe existing in the literature category proximity metrics as well as introduce three new ones, based on observing the properties of a multilabel Support Vector Machine classifier. The first metric uses classifier predictions, the second uses its errors, and the third is based on its model. Comparison to the existing state-of-the-art methods, and to manual assessments, confirm that the proposed methods are useful and are more flexible than typical approaches. We show how different metrics allow us to introduce new significant relations between categories. Aggregated results of mining categories' associations have been used to build a semantic network that shows a practical application of the research. The proposed method for finding associations can be extended with using other approaches than SVM classification, and can find (other than presented in the paper) applications for mining categories in text repositories. Eg.: it can be used for extending the prediction of the rating in recommender systems or as a method of missing data imputation.

Self-tuning and detector power is introduced to address improper coverage of NSA.Cooperation among agents makes correct identification of anomaly and lower FAR.EPAADPS improves anomaly detection and reduces FAR compared to state of art.Preventive mechanism identifies and contains novel and zero day attacks. Artificial Immune System (AIS) is inspired from Biological Immune System (BIS) and demonstrates a lot of interesting facets and intelligence that include self-learning, self adaption, self regulatory, distributed with self/non-self detection capabilities. Due to these astonishing qualities AIS are predominantly used in anomaly detection where anomalies are treated as non-self that needs to be detected. Therefore, AIS appears appropriate for development of a proactive system to identify and prevent novel and unseen anomalies. This paper presents "An Efficient Proactive Artificial Immune System based Anomaly Detection and Prevention System (EPAADPS)" which embodies immune attributes to distinguish self and non-self in quest to identify and prevent novel, unseen anomalies. Negative Selection Algorithm (NSA) is a key AIS concept and is used for anomaly detection in various publications. Despite its relative success, detector selection and thereafter anomaly detection demands a more effective algorithm. This paper put forwards concept of self-tuning of detectors and detector power in NSA with the intension to make a detector evolve and facilitate better and correct self and non-self coverage. Thereafter, agents accompanying detectors collaborate and communicate between themselves to proactively discover correct anomalies and then take appropriate preventive measures. The performance of EPAADPS is contrasted with closely related state of art RNS algorithm using real valued representation and Euclidean distance. Experimental results revels promising EPAADPS performance which very comfortably outperforms the RNS. Furthermore, these results also demonstrate that EPAADPS shows remarkable resilience and intelligence in detecting novel unseen anomalies and with preventive measures to overcome the threat perception.

This paper proposes a deep convolutional neural network for HAR using smartphone sensors.Experiments show that the proposed method derives relevant and more complex features.The method achieved an almost perfect classification on moving activities.It outperforms other state-of-the-art data mining techniques in HAR. Human activities are inherently translation invariant and hierarchical. Human activity recognition (HAR), a field that has garnered a lot of attention in recent years due to its high demand in various application domains, makes use of time-series sensor data to infer activities. In this paper, a deep convolutional neural network (convnet) is proposed to perform efficient and effective HAR using smartphone sensors by exploiting the inherent characteristics of activities and 1D time-series signals, at the same time providing a way to automatically and data-adaptively extract robust features from raw data. Experiments show that convnets indeed derive relevant and more complex features with every additional layer, although difference of feature complexity level decreases with every additional layer. A wider time span of temporal local correlation can be exploited (1?9-1?14) and a low pooling size (1?2-1?3) is shown to be beneficial. Convnets also achieved an almost perfect classification on moving activities, especially very similar ones which were previously perceived to be very difficult to classify. Lastly, convnets outperform other state-of-the-art data mining techniques in HAR for the benchmark dataset collected from 30 volunteer subjects, achieving an overall performance of 94.79% on the test set with raw sensor data, and 95.75% with additional information of temporal fast Fourier transform of the HAR data set.

Integrating return prediction of traditional time series models in portfolio formation can improve the performance of original portfolio optimization model. Since machine learning and deep learning models have shown overwhelming superiority than time series models, this paper combines return prediction in portfolio formation with two machine learning models, i.e., random forest (RF) and support vector regression (SVR), and three deep learning models, i.e., LSTM neural network, deep multilayer perceptron (DMLP) and convolutional neural network. To be specific, this paper first applies these prediction models for stock preselection before portfolio formation. Then, this paper incorporates their predictive results in advancing mean–variance (MV) and omega portfolio optimization models. In order to present the superiority of these models, portfolio models with autoregressive integrated moving average’s return prediction are used as benchmarks. Evaluation is based on historical data of 9 years from 2007 to 2015 of component stocks of China securities 100 index. Experimental results show that MV and omega models with RF return prediction, i.e., RF+MVF and RF+OF, outperform the other models. Further, RF+MVF is superior to RF+OF. Due to the high turnover of these two models, this paper discusses their performance after deducting the transaction fee cased by turnover. Experiments present that RF+MVF still performs the best among MVF models and omega model with SVR prediction (SVR+OF) performs the best among OF models. Moreover, RF+MVF performs better than SVR+OF and high turnover erodes nearly half of their total returns especially for RF+OF and RF+MVF. Therefore, this paper recommends investors to build MVF with RF return prediction for daily trading investment.

Smartphone sensing capabilities have enabled human activity recognition (HAR) solutions to better understand human behavior through computational techniques. However, such solutions have suffered from scalability problems due to the high consumption of computational resources (e.g. memory and processing) and the difficulty of acting in real time due to not observing data evolution over time. These problems occur because the HAR solutions for smartphones have been solved through offline learning with models limited by a data history. The disadvantage of this approach is that human activities constantly change over time and are strongly influenced by the physical environment and user profile. To overcome such problem, this paper proposes a novel low-cost learning algorithm called NOHAR (NOvelty discrete data stream for Human Activity Recognition), focused on continuous flow of data analysis. NOHAR is an online classification algorithm based on symbolic data generated by a discretization process using algorithms as SAX and SFA. The advantages of these algorithms are their abilities to compress and reduce the dimensionality of data. In addition, this paper proposes a new framework called DISTAR (DIscrete STream learning for Activity Recognition) focused on the data streaming analysis. Its goals include standardizing the development of online algorithms for symbolic data. Experimental results using three databases show that NOHAR is on average 33 times faster than the state of the art and can reduce memory consumption by an average of 99.97%.

Several algorithms have been proposed towards discovering the graphical structure of Bayesian networks. Most of these algorithms are restricted to observational data and some enable us to incorporate knowledge as constraints in terms of what can and cannot be discovered by an algorithm. A common type of such knowledge involves the temporal order of the variables in the data. For example, knowledge that event B occurs after observing A and hence, the constraint that B cannot cause A . This paper investigates real-world case studies that incorporate interesting properties of objective temporal variable order, and the impact these temporal constraints have on the learnt graph. The results show that most of the learnt graphs are subject to major modifications after incorporating incomplete temporal objective information. Because temporal information is widely viewed as a form of knowledge that is subjective, rather than as a form of data that tends to be objective, it is generally disregarded and reduced to an optional piece of information that only few of the structure learning algorithms may consider. The paper argues that objective temporal information should form part of observational data, to reduce the risk of disregarding such information when available and to encourage its reusability across related studies.

Indoor localization systems have the capability to change the way of providing location-based services in a closed environment. Though there is no agreed-upon technology that works best in indoor, WiFi signal is an important alternative as most of such places are covered by WiFi Access Points (APs). In this paper, the problem of indoor localization is investigated from the perspective of expert systems through applying machine learning techniques. The significant variation of WiFi signal strength with ambient conditions as well as device configuration badly affects the localization accuracy. Thus, the fingerprinting effort required to train a localization system subject to context heterogeneity is huge. The uncertainty in localization performance due to varying contexts is hardly investigated in the literature. Consequently, the main contribution of this paper is to propose a weighted ensemble classifier based on Dempster–Shafer belief theory to efficiently handle context heterogeneity. Here, the context is defined in terms of different smartphone configurations used for training and testing the system as well as temporal variation of signals. The method presented here utilizes the Dempster–Shafer theory of belief functions to calculate the weights of the base learners in the decision of the ensemble. Belief theory is applied here to handle the inherent uncertainty in WiFi signal variations due to heterogeneous context. Real life experiments are conducted for two datasets, JUIndoorLoc and UJIIndoorLoc at different granularity levels. For JUIndoorLoc, with state-of-the-art classifiers, 86–97% accuracy can be achieved for 10-fold cross-validation. However, when the training context differs from the test conditions, accuracy drops to 62–87%. In such a scenario, the proposed weighted ensemble technique is found to achieve almost 98% localization accuracy when RSSIs, mean and variance of RSSIs are considered as features. The technique can lead to an effective expert system for indoor localization at varying granularity levels. Such systems would be beneficial for pervasive indoor positioning applications as no dedicated infrastructure is needed for positioning.

This paper examines the option pricing performance of the most popular Machine Learning algorithms. The classic parametrical models suffer from several limitations in term of computational power required for parametric calibration and unrealistic economical and statistical assumptions. Therefore, a data driven approach based on non-parametric models is are well justified. Most of the previous researchers focus especially on the neural networks method (NN), the other algorithms being unexplored. Beside NN, this paper also analyses the performance of the Support Vector Regressions and Genetic Algorithms and propose three other Decision Tree methods, respectively Random Forest, XGBoost and LightGMB. In order to emphasize the power of this algorithms, a comparison with classical methods like Black-Scholes and Corrado-Su with both historical and implied parameters have been conducted. The analyzes were performed on European call options who have as underlying asset the WTI crude oil future contracts. Machine Learning algorithms outperform by a great margin the classical approaches regardless of the moneyness and the maturity of the contracts.

In this paper, a case study on the role of fuzzy logic (FL) in data mining and machine learning is carried out. It is outlined that, in order to draw more attention of data-mining and machine-learning communities to FL, studies on FL could be more focused not on the activities that fuzzy methods can perform better but rather on the activities that fuzzy methods can perform and the non-fuzzy ones can’t. Such approach takes us away from discussing quantitative differences between fuzzy and non-fuzzy methods to discussing qualitative differences, which are possibly more favorable objects of scientific curiosity. Following the outlined suggestion, a novel speed-up technique is proposed in this paper to support association rule mining (ARM). The proposed technique is a clustering-based one and provides fusion of clustering and ARM. The catchy feature of this technique is that it works well if applied in fuzzy ARM and doesn’t work well if applied in non-fuzzy ARM. The proposed technique is put through experimental verification involving several real-world datasets, and the results substantiate its effectiveness.

This paper proposes a novel approach to the portfolio management using an AutoEncoder. In particular, features learned by an AutoEncoder with ReLU are directly exploited to portfolio constructions. Since the AutoEncoder extracts characteristics of data through a non-linear activation function ReLU, its realization is generally difficult due to the non-linear transformation procedure. In the current paper, we solve this problem by taking full advantage of the similarity of ReLU and an option payoff. Especially, this paper shows that the features are successfully replicated by applying so-called dynamic delta hedging strategy. An out of sample simulation with crypto currency dataset shows the effectiveness of our proposed strategy.

To develop an advanced CBR system to well adapt to the intelligence implementation of new engineering process in the big data environment, Bayesian network (BN) model is introduced to CBR system for knowledge reasoning. However, as engineering application is becoming more and more complicated, the number of parameters used to define engineering application grows larger and larger, leading to the seriously reduced efficiency as well as the accuracy of the integrated model. For the problem of reduced efficiency, this paper proposes In-External (IE) algorithm to perform the assignment of big data distribution for parallel data processing, which can fully utilize the capacity of Hadoop system and attain the best efficiency of knowledge reasoning. For the problem of reduced accuracy, in view of the fact that traditional probability learning methods are unfit for the proposed CBR system, this paper proposes Discount Exponential Coefficients of Multivariate Beta Distribution (DECMBD) algorithm to conduct the probability learning of proposed system. In DECMBD algorithm, a discount ratio is given to each exponential coefficient of multivariate Beta distribution to improve the occurrence times counting of all problem features and then gain better effect of probability learning. Finally, lots of experiments are performed to validate the effectiveness of the proposed advanced CBR system.

A new technique for instance selection and noise filtering for regression is proposed.The method use instance selection for classification after output value discretization.The method is much simpler and more robust to noise than other specifically designed for regression. An important step in building expert and intelligent systems is to obtain the knowledge that they will use. This knowledge can be obtained from experts or, nowadays more often, from machine learning processes applied to large volumes of data. However, for some of these learning processes, if the volume of data is large, the knowledge extraction phase is very slow (or even impossible). Moreover, often the origin of the data sets used for learning are measure processes in which the collected data can contain errors, so the presence of noise in the data is inevitable. It is in such environments where an initial step of noise filtering and reduction of data set size plays a fundamental role. For both tasks, instance selection emerges as a possible solution that has proved to be useful in various fields. In this paper we focus mainly on instance selection for noise removal. In addition, in contrast to most of the existing methods, which applied instance selection to classification tasks (discrete prediction), the proposed approach is used to obtain instance selection methods for regression tasks (prediction of continuous values). The different nature of the value to predict poses an extra difficulty that explains the low number of articles on the subject of instance selection for regression.More specifically the idea used in this article to adapt to regression problems "classic" instance-selection algorithms for classification is as simple as the discretization of the numerical output variable. In the experimentation, the proposed method is compared with much more sophisticated methods, specifically designed for regression, and shows to be very competitive.The main contributions of the paper include: (i) a simple way to adapt to regression instance selection algorithms for classification, (ii) the use of this approach to adapt a popular noise filter called ENN (edited nearest neighbor), and (iii) the comparison of this noise filter against two other specifically designed for regression, showing to be very competitive despite its simplicity.

The paper focuses in short-term bus load forecasting.Three forecasting models are proposed and tested.The load profiling methodology is combined with neural network. Artificial neural networks (ANNs) are a favorable scheme in load forecasting applications mainly due to their endogenous capacity of robust modeling of data sets with highly non-linear relationship between inputs and outputs. Usually, the inputs correspond to historical load values, exogenous variables like temperature, day type identification codes and others. The outputs refer to the load values under examination. The majority of the load forecasting related literature focuses in aggregated load system level. While contemporary research efforts focus in smart grid technologies, there is need to study the characteristics of small scaled loads. Bus load forecasting refers to prediction of the demand patterns in buses of the transmission and distribution systems. Bus load exhibits low correlation with the aggregated system load, since it is characterized by a high level of stochasticity. Hence, a proper selection and formulation of the forecasting model is essential in order to keep the prediction accuracy within acceptable ranges. The treatment of bus load characteristics is held with computational intelligence techniques such as clustering and ANN. Neural network based systems are a favorable scheme in recent years in price and load predictions over traditional time series models. ANN can fully adapt expert knowledge and modify their parameters accordingly to simulate the problem`s attributions through training paradigms. Thus, ANN based systems are an essential choice, justified by the paper`s findings, for highly volatile time series. This work focuses on the short-term load forecasting (STLF) of a number of buses within the Greek interconnected system. Firstly, a modified version of the ANN already proposed for the aggregated load of the interconnected system is employed. To enhance the forecasting accuracy of the ANN, the load profiling methodology is used resulting to the formulation of two novel hybrid forecasting models. These models refer to the combination of the ANN with a clustering algorithm, resulting to superior performance. Simulation results indicate that the combination captures and successfully treats the special characteristics of the bus load patterns. The scope of the present paper is to develop efficient forecasting systems for short-term bus load predictions. This is a current research challenge due to the high interest for smart grids and demand side management applications by utilities, regulators, retailer and energy service companies. Bus load forecasting appears to be a more difficult engineering problem compared to forecasting of the total load of a country. No hybrid models for bus load predictions have been presented so far in the literature. Two novel clustering based tools are developed and successfully tested in a number of loads covering different types of electricity consumers and demand levels.

Currently FOREX (foreign exchange market) is the largest financial market over the world. Usually the Forex market analysis is based on the Forex time series prediction. Nevertheless, trading expert systems based on such predictions do not usually provide satisfactory results. On the other hand, stock trading expert systems called also “mechanical trading systems”, which are based on the technical analysis, are very popular and may provide good profits. Therefore, in this paper we propose a Forex trading expert system based on some new technical analysis indicators and a new approach to the rule-base evidential reasoning (RBER) (the synthesis of fuzzy logic and the Dempster–Shafer theory of evidence). We have found that the traditional fuzzy logic rules lose an important information, when dealing with the intersecting fuzzy classes, e.g., such as Low and Medium and we have shown that this property may lead to the controversial results in practice. In the framework of the proposed in the current paper new approach, an information of the values of all membership functions representing the intersecting (competing) fuzzy classes is preserved and used in the fuzzy logic rules. The advantages of the proposed approach are demonstrated using the developed expert system optimized and tested on the real data from the Forex market for the four currency pairs and the time frames 15 m, 30 m, 1 h and 4 h.