Search

Analyzing and predicting the trend of price fluctuation has been receiving more and more attention, as price risk has become the focus of risk control research in heating oil futures market. A novel time series prediction model combined with the complex network method is put forward in the paper. First of all, this paper counts the cumulative time interval of different nodes in the network, and fits its growth trend with the Fourier model. Then a novel price fluctuation prediction model is established based on the effective information such as some topology properties extracted from the network. The results show that the Fourier model can predict the emergence time of new nodes in the next stage, and the established price fluctuation prediction model can infer the names of nodes in the prediction interval, so as to determine the forward-looking behavior of price evolution. Besides, liken to the NAR neural network, the prediction results obtained by the proposed method also show superiority, which has important theoretical value and academic significance for early warning and prediction of price behavior in the heating oil futures market. [ABSTRACT FROM AUTHOR]

Ensembles are a well established machine learning paradigm, leading to accurate and robust models, predominantly applied to predictive modeling tasks. Ensemble models comprise a finite set of diverse predictive models whose combined output is expected to yield an improved predictive performance as compared to an individual model. In this paper, we propose a new method for learning ensembles of process-based models of dynamic systems. The process-based modeling paradigm employs domain-specific knowledge to automatically learn models of dynamic systems from time-series observational data. Previous work has shown that ensembles based on sampling observational data (i.e., bagging and boosting), significantly improve predictive performance of process-based models. However, this improvement comes at the cost of a substantial increase of the computational time needed for learning. To address this problem, the paper proposes a method that aims at efficiently learning ensembles of process-based models, while maintaining their accurate long-term predictive performance. This is achieved by constructing ensembles with sampling domain-specific knowledge instead of sampling data. We apply the proposed method to and evaluate its performance on a set of problems of automated predictive modeling in three lake ecosystems using a library of process-based knowledge for modeling population dynamics. The experimental results identify the optimal design decisions regarding the learning algorithm. The results also show that the proposed ensembles yield significantly more accurate predictions of population dynamics as compared to individual process-based models. Finally, while their predictive performance is comparable to the one of ensembles obtained with the state-of-the-art methods of bagging and boosting, they are substantially more efficient. [ABSTRACT FROM AUTHOR]

Recommender systems are vulnerable to shilling attacks. Forged user-generated content data, such as user ratings and reviews, are used by attackers to manipulate recommendation rankings. Shilling attack detection in recommender systems is of great significance to maintain the fairness and sustainability of recommender systems. The current studies have problems in terms of the poor universality of algorithms, difficulty in selection of user profile attributes, and lack of an optimization mechanism. In this paper, a shilling behaviour detection structure based on abnormal group user findings and rating time series analysis is proposed. This paper adds to the current understanding in the field by studying the credibility evaluation model in-depth based on the rating prediction model to derive proximity-based predictions. A method for detecting suspicious ratings based on suspicious time windows and target item analysis is proposed. Suspicious rating time segments are determined by constructing a time series, and data streams of the rating items are examined and suspicious rating segments are checked. To analyse features of shilling attacks by a group user’s credibility, an abnormal group user discovery method based on time series and time window is proposed. Standard testing datasets are used to verify the effect of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we propose a hybrid method to forecast the stock prices called High-order-fuzzy-fluctuation-Trends-based Back Propagation(HTBP)Neural Network model. First, we compare each value of the historical training data with the previous day's value to obtain a fluctuation trend time series (FTTS). On this basis, the FTTS blur into fuzzy time series (FFTS) based on the fluctuation of the increasing, equality, decreasing amplitude and direction. Since the relationship between FFTS and future wave trends is nonlinear, the HTBP neural network algorithm is used to find the mapping rules in the form of self-learning. Finally, the results of the algorithm output are used to predict future fluctuations. The proposed model provides some innovative features:(1)It combines fuzzy set theory and neural network algorithm to avoid overfitting problems existed in traditional models. (2)BP neural network algorithm can intelligently explore the internal rules of the actual existence of sequential data, without the need to analyze the influence factors of specific rules and the path of action. (3)The hybrid modal can reasonably remove noises from the internal rules by proper fuzzy treatment. This paper takes the TAIEX data set of Taiwan stock exchange as an example, and compares and analyzes the prediction performance of the model. The experimental results show that this method can predict the stock market in a very simple way. At the same time, we use this method to predict the Shanghai stock exchange composite index, and further verify the effectiveness and universality of the method. [ABSTRACT FROM AUTHOR]

Several lifetime distributions have played an important role to fit survival data. However, for some of these models, the computation of maximum likelihood estimators is quite difficult due to presence of flat regions in the search space, among other factors. Several well-known derivative-based optimization tools are unsuitable for obtaining such estimates. To circumvent this problem, we introduce the AdequacyModel computational library version 2.0.0 for the R statistical environment with two major contributions: a general optimization technique based on the Particle Swarm Optimization (PSO) method (with a minor modification of the original algorithm) and a set of statistical measures for assessment of the adequacy of the fitted model. This library is very useful for researchers in probability and statistics and has been cited in various papers in these areas. It serves as the basis for the Newdistns library (version 2.1) published in an impact journal in the area of computational statistics, see . It is also the basis of the Wrapped library (version 2.0), see . A third package making use of the AdequacyModel library can be found in . In addition, the proposed library has proved to be very useful for maximizing log-likelihood functions with complex search regions. The library provides a greater control of the optimization process by introducing a stop criterion based on a minimum number of iterations and the variance of a given proportion of optimal values. We emphasize that the new library can be used not only in statistics but in physics and mathematics as proved in several examples throughout the paper. [ABSTRACT FROM AUTHOR]

This paper proposes a method to predict fluctuations in the prices of cryptocurrencies, which are increasingly used for online transactions worldwide. Little research has been conducted on predicting fluctuations in the price and number of transactions of a variety of cryptocurrencies. Moreover, the few methods proposed to predict fluctuation in currency prices are inefficient because they fail to take into account the differences in attributes between real currencies and cryptocurrencies. This paper analyzes user comments in online cryptocurrency communities to predict fluctuations in the prices of cryptocurrencies and the number of transactions. By focusing on three cryptocurrencies, each with a large market size and user base, this paper attempts to predict such fluctuations by using a simple and efficient method. [ABSTRACT FROM AUTHOR]

In a recidivism prediction context, there is no consensus on which modeling strategy should be followed for obtaining an optimal prediction model. In previous papers, a range of statistical and machine learning techniques were benchmarked on recidivism data with a binary outcome. However, two important tree ensemble methods, namely gradient boosting and random forests were not extensively evaluated. In this paper, we further explore the modeling potential of these techniques in the binary outcome criminal prediction context. Additionally, we explore the predictive potential of classical statistical and machine learning methods for censored time-to-event data. A range of statistical manually specified statistical and (semi-)automatic machine learning models is fitted on Dutch recidivism data, both for the binary outcome case and censored outcome case. To enhance generalizability of results, the same models are applied to two historical American data sets, the North Carolina prison data. For all datasets, (semi-) automatic modeling in the binary case seems to provide no improvement over an appropriately manually specified traditional statistical model. There is however evidence of slightly improved performance of gradient boosting in survival data. Results on the reconviction data from two sources suggest that both statistical and machine learning should be tried out for obtaining an optimal model. Even if a flexible black-box model does not improve upon the predictions of a manually specified model, it can serve as a test whether important interactions are missing or other misspecification of the model are present and can thus provide more security in the modeling process. [ABSTRACT FROM AUTHOR]

A wide variety of methods have been proposed in protein subnuclear localization to improve the prediction accuracy. However, one important trend of these means is to treat fusion representation by fusing multiple feature representations, of which, the fusion process takes a lot of time. In view of this, this paper novelly proposed a method by combining a new single feature representation and a new algorithm to obtain good recognition rate. Specifically, based on the position-specific scoring matrix (PSSM), we proposed a new expression, correlation position-specific scoring matrix (CoPSSM) as the protein feature representation. Based on the classic nonlinear dimension reduction algorithm, kernel linear discriminant analysis (KLDA), we added a new discriminant criterion and proposed a dichotomous greedy genetic algorithm (DGGA) to intelligently select its kernel bandwidth parameter. Two public datasets with Jackknife test and KNN classifier were used for the numerical experiments. The results showed that the overall success rate (OSR) with single representation CoPSSM is larger than that with many relevant representations. The OSR of the proposed method can reach as high as 87.444% and 90.3361% for these two datasets, respectively, outperforming many current methods. To show the generalization of the proposed algorithm, two extra standard datasets of protein subcellular were chosen to conduct the expending experiment, and the prediction accuracy by Jackknife test and Independent test is still considerable. [ABSTRACT FROM AUTHOR]

In recent years, with the development of computer science, deep learning is held as competent enough to solve the problem of inference and learning in high dimensional space. Therefore, it has received unprecedented attention from both the academia and the business community. Compared with CPU/GPU, FPGA has attracted much attention for its high-energy efficiency, short development cycle and reconfigurability in the aspect of deep learning algorithm. However, because of the limited research on OpenCL optimization on FPGA of deep learning algorithms, OpenCL tools and models applied to CPU/GPU cannot be directly used on FPGA. This makes it difficult for software programmers to use FPGA when implementing deep learning algorithms for a rewarding performance. To solve this problem, this paper proposed an OpenCL computational model based on FPGA template architecture to optimize the time-consuming convolution layer in deep learning. The comparison between the program applying the computational model and the corresponding optimization program provided by Xilinx indicates that the former is 8-40 times higher than the latter in terms of performance. [ABSTRACT FROM AUTHOR]

Temporal hierarchies have been widely used during the past few years as they are capable to provide more accurate coherent forecasts at different planning horizons. However, they still display some limitations, being mainly subject to the forecasting methods used for generating the base forecasts and the particularities of the examined series. This paper deals with such limitations by considering three different strategies: (i) combining forecasts of multiple methods, (ii) applying bias adjustments and (iii) selectively implementing temporal hierarchies to avoid seasonal shrinkage. The proposed strategies can be applied either separately or simultaneously, being complements to the method considered for reconciling the base forecasts and completely independent from each other. Their effect is evaluated using the monthly series of the M and M3 competitions. The results are very promising, displaying lots of potential for improving the performance of temporal hierarchies, both in terms of accuracy and bias. [ABSTRACT FROM AUTHOR]

Filter or screening methods are often used as a preprocessing step for reducing the number of variables used by a learning algorithm in obtaining a classification or regression model. While there are many such filter methods, there is a need for an objective evaluation of these methods. Such an evaluation is needed to compare them with each other and also to answer whether they are at all useful, or a learning algorithm could do a better job without them. For this purpose, many popular screening methods are partnered in this paper with three regression learners and five classification learners and evaluated on ten real datasets to obtain accuracy criteria such as R-square and area under the ROC curve (AUC). The obtained results are compared through curve plots and comparison tables in order to find out whether screening methods help improve the performance of learning algorithms and how they fare with each other. Our findings revealed that the screening methods were useful in improving the prediction of the best learner on two regression and two classification datasets out of the ten datasets evaluated. [ABSTRACT FROM AUTHOR]

In this paper, we propose a human action recognition method using HOIRM (histogram of oriented interest region motion) feature fusion and a BOW (bag of words) model based on AP (affinity propagation) clustering. First, a HOIRM feature extraction method based on spatiotemporal interest points ROI is proposed. HOIRM can be regarded as a middle-level feature between local and global features. Then, HOIRM is fused with 3D HOG and 3D HOF local features using a cumulative histogram. The method further improves the robustness of local features to camera view angle and distance variations in complex scenes, which in turn improves the correct rate of action recognition. Finally, a BOW model based on AP clustering is proposed and applied to action classification. It obtains the appropriate visual dictionary capacity and achieves better clustering effect for the joint description of a variety of features. The experimental results demonstrate that by using the fused features with the proposed BOW model, the average recognition rate is 95.75% in the KTH database, and 88.25% in the UCF database, which are both higher than those by using only 3D HOG+3D HOF or HOIRM features. Moreover, the average recognition rate achieved by the proposed method in the two databases is higher than that obtained by other methods. [ABSTRACT FROM AUTHOR]

The performance of data clustering algorithms is mainly dependent on their ability to balance between the exploration and exploitation of the search process. Although some data clustering algorithms have achieved reasonable quality solutions for some datasets, their performance across real-life datasets could be improved. This paper proposes an adaptive memetic differential evolution optimisation algorithm (AMADE) for addressing data clustering problems. The memetic algorithm (MA) employs an adaptive differential evolution (DE) mutation strategy, which can offer superior mutation performance across many combinatorial and continuous problem domains. By hybridising an adaptive DE mutation operator with the MA, we propose that it can lead to faster convergence and better balance the exploration and exploitation of the search. We would also expect that the performance of AMADE to be better than MA and DE if executed separately. Our experimental results, based on several real-life benchmark datasets, shows that AMADE outperformed other compared clustering algorithms when compared using statistical analysis. We conclude that the hybridisation of MA and the adaptive DE is a suitable approach for addressing data clustering problems and can improve the balance between global exploration and local exploitation of the optimisation algorithm. [ABSTRACT FROM AUTHOR]

In general, the stock prices of the same industry have a similar trend, but those of different industries do not. When investing in stocks of different industries, one should select the optimal model from lots of trading models for each industry because any model may not be suitable for capturing the stock trends of all industries. However, the study has not been carried out at present. In this paper, firstly we select 424 S&P 500 index component stocks (SPICS) and 185 CSI 300 index component stocks (CSICS) as the research objects from 2010 to 2017, divide them into 9 industries such as finance and energy respectively. Secondly, we apply 12 widely used machine learning algorithms to generate stock trading signals in different industries and execute the back-testing based on the trading signals. Thirdly, we use a non-parametric statistical test to evaluate whether there are significant differences among the trading performance evaluation indicators (PEI) of different models in the same industry. Finally, we propose a series of rules to select the optimal models for stock investment of every industry. The analytical results on SPICS and CSICS show that we can find the optimal trading models for each industry based on the statistical tests and the rules. Most importantly, the PEI of the best algorithms can be significantly better than that of the benchmark index and “Buy and Hold” strategy. Therefore, the algorithms can be used for making profits from industry stock trading. [ABSTRACT FROM AUTHOR]

Archaeologists often need to date and group artifact types to discern typologies, chronologies, and classifications. For over a century, statisticians have been using classification and clustering techniques to infer patterns in data that can be defined by algorithms. In the case of archaeology, linear regression algorithms are often used to chronologically date features and sites, and pattern recognition is used to develop typologies and classifications. However, archaeological data is often expensive to collect, and analyses are often limited by poor sample sizes and datasets. Here we show that recent advances in computation allow archaeologists to use machine learning based on much of the same statistical theory to address more complex problems using increased computing power and larger and incomplete datasets. This paper approaches the problem of predicting the chronology of archaeological sites through a case study of medieval temples in Angkor, Cambodia. For this study, we have a large dataset of temples with known architectural elements and artifacts; however, less than ten percent of the sample of temples have known dates, and much of the attribute data is incomplete. Our results suggest that the algorithms can predict dates for temples from 821–1150 CE with a 49-66-year average absolute error. We find that this method surpasses traditional supervised and unsupervised statistical approaches for under-specified portions of the dataset and is a promising new method for anthropological inquiry. [ABSTRACT FROM AUTHOR]

Deep learning techniques, e.g., Convolutional Neural Networks (CNNs), have been explosively applied to the research in the fields of information retrieval and natural language processing. However, few research efforts have addressed semantic indexing with deep learning. The use of semantic indexing in the biomedical literature has been limited for several reasons. For instance, MEDLINE citations contain a large number of semantic labels from automatically annotated MeSH terms, and for a great deal of the literature, only the information of the title and the abstract is readily available. In this paper, we propose a Boltzmann Convolutional neural network framework (B-CNN) for biomedicine semantic indexing. In our hybrid learning framework, the CNN can adaptively deal with features of documents that have sequence relationships, and can capture context information accordingly; the Deep Boltzmann Machine (DBM) merges global (the entity in each document) and local information through its training with undirected connections. Additionally, we have designed a hierarchical coarse to fine style indexing structure for learning and classifying documents, and a novel feature extension approach with word sequence embedding and Wikipedia categorization. Comparative experiments were conducted for semantic indexing of biomedical abstract documents; these experiments verified the encouraged performance of our B-CNN model. [ABSTRACT FROM AUTHOR]

In this paper, we propose a face recognition algorithm based on a combination of vector quantization (VQ) and Markov stationary features (MSF). The VQ algorithm has been shown to be an effective method for generating features; it extracts a codevector histogram as a facial feature representation for face recognition. Still, the VQ histogram features are unable to convey spatial structural information, which to some extent limits their usefulness in discrimination. To alleviate this limitation of VQ histograms, we utilize Markov stationary features (MSF) to extend the VQ histogram-based features so as to add spatial structural information. We demonstrate the effectiveness of our proposed algorithm by achieving recognition results superior to those of several state-of-the-art methods on publicly available face databases. [ABSTRACT FROM AUTHOR]

DNA-binding proteins play pivotal roles in alternative splicing, RNA editing, methylating and many other biological functions for both eukaryotic and prokaryotic proteomes. Predicting the functions of these proteins from primary amino acids sequences is becoming one of the major challenges in functional annotations of genomes. Traditional prediction methods often devote themselves to extracting physiochemical features from sequences but ignoring motif information and location information between motifs. Meanwhile, the small scale of data volumes and large noises in training data result in lower accuracy and reliability of predictions. In this paper, we propose a deep learning based method to identify DNA-binding proteins from primary sequences alone. It utilizes two stages of convolutional neutral network to detect the function domains of protein sequences, and the long short-term memory neural network to identify their long term dependencies, an binary cross entropy to evaluate the quality of the neural networks. When the proposed method is tested with a realistic DNA binding protein dataset, it achieves a prediction accuracy of 94.2% at the Matthew’s correlation coefficient of 0.961. Compared with the LibSVM on the arabidopsis and yeast datasets via independent tests, the accuracy raises by 9% and 4% respectively. Comparative experiments using different feature extraction methods show that our model performs similar accuracy with the best of others, but its values of sensitivity, specificity and AUC increase by 27.83%, 1.31% and 16.21% respectively. Those results suggest that our method is a promising tool for identifying DNA-binding proteins. [ABSTRACT FROM AUTHOR]

Broken water pumps continue to impede efforts to deliver clean and economically-viable water to the global poor. The literature has demonstrated that customers’ health benefits and willingness to pay for clean water are best realized when clean water infrastructure performs extremely well (>99% uptime). In this paper, we used sensor data from 42 Afridev-brand handpumps observed for 14 months in western Kenya to demonstrate how sensors and supervised ensemble machine learning could be used to increase total fleet uptime from a best-practices baseline of about 70% to >99%. We accomplish this increase in uptime by forecasting pump failures and identifying existing failures very quickly. Comparing the costs of operating the pump per functional year over a lifetime of 10 years, we estimate that implementing this algorithm would save 7% on the levelized cost of water relative to a sensor-less scheduled maintenance program. Combined with a rigorous system for dispatching maintenance personnel, implementing this algorithm in a real-world program could significantly improve health outcomes and customers’ willingness to pay for water services. [ABSTRACT FROM AUTHOR]

Music emotion recognition (MER) field rapidly expanded in the last decade. Many new methods and new audio features are developed to improve the performance of MER algorithms. However, it is very difficult to compare the performance of the new methods because of the data representation diversity and scarcity of publicly available data. In this paper, we address these problems by creating a data set and a benchmark for MER. The data set that we release, a MediaEval Database for Emotional Analysis in Music (DEAM), is the largest available data set of dynamic annotations (valence and arousal annotations for 1,802 songs and song excerpts licensed under Creative Commons with 2Hz time resolution). Using DEAM, we organized the ‘Emotion in Music’ task at MediaEval Multimedia Evaluation Campaign from 2013 to 2015. The benchmark attracted, in total, 21 active teams to participate in the challenge. We analyze the results of the benchmark: the winning algorithms and feature-sets. We also describe the design of the benchmark, the evaluation procedures and the data cleaning and transformations that we suggest. The results from the benchmark suggest that the recurrent neural network based approaches combined with large feature-sets work best for dynamic MER. [ABSTRACT FROM AUTHOR]

Prediction of memory performance (remembered or forgotten) has various potential applications not only for knowledge learning but also for disease diagnosis. Recently, subsequent memory effects (SMEs)—the statistical differences in electroencephalography (EEG) signals before or during learning between subsequently remembered and forgotten events—have been found. This finding indicates that EEG signals convey the information relevant to memory performance. In this paper, based on SMEs we propose a computational approach to predict memory performance of an event from EEG signals. We devise a convolutional neural network for EEG, called ConvEEGNN, to predict subsequently remembered and forgotten events from EEG recorded during memory process. With the ConvEEGNN, prediction of memory performance can be achieved by integrating two main stages: feature extraction and classification. To verify the proposed approach, we employ an auditory memory task to collect EEG signals from scalp electrodes. For ConvEEGNN, the average prediction accuracy was 72.07% by using EEG data from pre-stimulus and during-stimulus periods, outperforming other approaches. It was observed that signals from pre-stimulus period and those from during-stimulus period had comparable contributions to memory performance. Furthermore, the connection weights of ConvEEGNN network can reveal prominent channels, which are consistent with the distribution of SME studied previously. [ABSTRACT FROM AUTHOR]

The remaining useful life (RUL) prediction of Lithium-ion batteries is closely related to the capacity degeneration trajectories. Due to the self-charging and the capacity regeneration, the trajectories have the property of multimodality. Traditional prediction models such as the support vector machines (SVM) or the Gaussian Process regression (GPR) cannot accurately characterize this multimodality. This paper proposes a novel RUL prediction method based on the Gaussian Process Mixture (GPM). It can process multimodality by fitting different segments of trajectories with different GPR models separately, such that the tiny differences among these segments can be revealed. The method is demonstrated to be effective for prediction by the excellent predictive result of the experiments on the two commercial and chargeable Type 1850 Lithium-ion batteries, provided by NASA. The performance comparison among the models illustrates that the GPM is more accurate than the SVM and the GPR. In addition, GPM can yield the predictive confidence interval, which makes the prediction more reliable than that of traditional models. [ABSTRACT FROM AUTHOR]

This work is motivated by the needs of predictive analytics on healthcare data as represented by Electronic Medical Records. Such data is invariably problematic: noisy, with missing entries, with imbalance in classes of interests, leading to serious bias in predictive modeling. Since standard data mining methods often produce poor performance measures, we argue for development of specialized techniques of data-preprocessing and classification. In this paper, we propose a new method to simultaneously classify large datasets and reduce the effects of missing values. It is based on a multilevel framework of the cost-sensitive SVM and the expected maximization imputation method for missing values, which relies on iterated regression analyses. We compare classification results of multilevel SVM-based algorithms on public benchmark datasets with imbalanced classes and missing values as well as real data in health applications, and show that our multilevel SVM-based method produces fast, and more accurate and robust classification results. [ABSTRACT FROM AUTHOR]

The user-based collaborative filtering (CF) algorithm is one of the most popular approaches for making recommendation. Despite its success, the traditional user-based CF algorithm suffers one serious problem that it only measures the influence between two users based on their symmetric similarities calculated by their consumption histories. It means that, for a pair of users, the influences on each other are the same, which however may not be true. Intuitively, an expert may have an impact on a novice user but a novice user may not affect an expert at all. Besides, each user may possess a global importance factor that affects his/her influence to the remaining users. To this end, in this paper, we propose an asymmetric user influence model to measure the directed influence between two users and adopt the PageRank algorithm to calculate the global importance value of each user. And then the directed influence values and the global importance values are integrated to deduce the final influence values between two users. Finally, we use the final influence values to improve the performance of the traditional user-based CF algorithm. Extensive experiments have been conducted, the results of which have confirmed that both the asymmetric user influence model and global importance value play key roles in improving recommendation accuracy, and hence the proposed method significantly outperforms the existing recommendation algorithms, in particular the user-based CF algorithm on the datasets of high rating density. [ABSTRACT FROM AUTHOR]

The explosive growth of social networks in recent times has presented a powerful source of information to be utilized as an extra source for assisting in the social recommendation problems. The social recommendation methods that are based on probabilistic matrix factorization improved the recommendation accuracy and partly solved the cold-start and data sparsity problems. However, these methods only exploited the explicit social relations and almost completely ignored the implicit social relations. In this article, we firstly propose an algorithm to extract the implicit relation in the undirected graphs of social networks by exploiting the link prediction techniques. Furthermore, we propose a new probabilistic matrix factorization method to alleviate the data sparsity problem through incorporating explicit friendship and implicit friendship. We evaluate our proposed approach on two real datasets, Last.Fm and Douban. The experimental results show that our method performs much better than the state-of-the-art approaches, which indicates the importance of incorporating implicit social relations in the recommendation process to address the poor prediction accuracy. [ABSTRACT FROM AUTHOR]

Patterns of spatial behavior dictate how we use our infrastructure, encounter other people, or are exposed to services and opportunities. Understanding these patterns through the analysis of data commonly available through commodity smartphones has become an important arena for innovation in both academia and industry. The resulting datasets can quickly become massive, indicating the need for concise understanding of the scope of the data collected. Some data is obviously correlated (for example GPS location and which WiFi routers are seen). Codifying the extent of these correlations could identify potential new models, provide guidance on the amount of data to collect, and even provide actionable features. However, identifying correlations, or even the extent of correlation, is difficult because the form of the correlation must be specified. Fractal-based intrinsic dimensionality directly calculates the minimum number of dimensions required to represent a dataset. We provide an intrinsic dimensionality analysis of four smartphone datasets over seven input dimensions, and empirically demonstrate an intrinsic dimension of approximately two. [ABSTRACT FROM AUTHOR]

The study shows the feasibility of predicting firms’ expenditures in innovation, as reported in the Community Innovation Survey, applying a supervised machine-learning approach on a sample of Italian firms. Using an integrated dataset of administrative records and balance sheet data, designed to include all informative variables related to innovation but also easily accessible for most of the cohort, random forest algorithm is implemented to obtain a classification model aimed to identify firms that are potential innovation performers. The performance of the classifier, estimated in terms of AUC, is 0.794. Although innovation investments do not always result in patenting, the model is able to identify 71.92% of firms with patents. More encouraging results emerge from the analysis of the inner working of the model: predictors identified as most important—such as firm size, sector belonging and investment in intangible assets—confirm previous findings of literature, but in a completely different framework. The outcomes of this study are considered relevant for both economic analysts, because it demonstrates the potential of data-driven models for understanding the nature of innovation behaviour, and practitioners, such as policymakers or venture capitalists, who can benefit by evidence-based tools in the decision-making process. [ABSTRACT FROM AUTHOR]

Objectives: We propose a bottom-up, machine-learning approach, for the objective vestibular and balance diagnostic data of concussion patients, to provide insight into the differences in patients’ phenotypes, independent of existing diagnoses (unsupervised learning). Methods: Diagnostic data from a battery of validated balance and vestibular assessments were extracted from the database of the Swiss Concussion Center. The desired number of clusters within the patient database was estimated using Calinski-Harabasz criteria. Complex (self-organizing map, SOM) and standard (k-means) clustering tools were used, and the formed clusters were compared. Results: A total of 96 patients (81.3% male, age (median [IQR]): 25.0[10.8]) who were expected to suffer from sports-related concussion or post-concussive syndrome (52[140] days between diagnostic testing and the concussive episode) were included. The cluster evaluation indicated dividing the data into two groups. Only the SOM gave a stable clustering outcome, dividing the patients in group-1 (n = 38) and group-2 (n = 58). A large significant difference was found for the caloric summary score for the maximal speed of the slow phase, where group-1 scored 30.7% lower than group-2 (27.6[18.2] vs. 51.0[31.0]). Group-1 also scored significantly lower on the sensory organisation test composite score (69.0[22.3] vs. 79.0[10.5]) and higher on the visual acuity (-0.03[0.33] vs. -0.14[0.12]) and dynamic visual acuity (0.38[0.84] vs. 0.20[0.20]) tests. The importance of caloric, SOT and DVA, was supported by the PCA outcomes. Group-1 tended to report headaches, blurred vision and balance problems more frequently than group-2 (>10% difference). Conclusion: The SOM divided the data into one group with prominent vestibular disorders and another with no clear vestibular or balance problems, suggesting that artificial intelligence might help improve the diagnostic process. [ABSTRACT FROM AUTHOR]

A Recommender System (RS) is an intelligent system that assists users in finding the items of their interest (e.g. books, movies, music) by preventing them to go through huge piles of data available online. In an effort to overcome the data sparsity issue in recommender systems, this research incorporates a content based filtering technique with fuzzy inference system and a conformal prediction approach introducing a new framework called Hybrid Content based Fuzzy Conformal Recommender System (HCF-CRS). The proposed framework is implemented to be used in the domain of movies and it provides quality recommendations to users with a confidence level and an improved accuracy. In our proposed framework, first, a Content Based Filtering (CBF) technique is applied to create a user profile by considering the history of each user. CBF is useful in the situations like: lack of demographic information and the data sparsity problems. Second, a Fuzzy based technique is incorporated to find the similarities and differences between the user profile and the movies in the dataset using a set of fuzzy rules to get a predicted rating for each movie. Third, a Conformal prediction algorithm is implemented to calculate the non-conformity measure between the predicted ratings produced by fuzzy system and the actual ratings from the dataset. A p-value (confidence measure) is computed to give a level of confidence to each recommended item and a bound is set on the confidence level called a significance level ε, according to which the movies only above the specified significance level are recommended to user. By building a confidence centric hybrid conformal recommender system using the content based filtering approach with fuzzy logic and conformal prediction algorithm, the reliability and the accuracy of the system is considerably enhanced. The experiments are evaluated on MovieLens and Movie Tweetings datasets for recommending movies to the users and they are compared with other state-of-the-art recommender systems. Finally, the results confirm that the proposed algorithms perform better than the traditional ones. [ABSTRACT FROM AUTHOR]

It is becoming increasingly clear that major malignancies such as breast, colorectal and gastric cancers are not single disease entities, but comprising multiple cancer subtypes of distinct molecular properties. Molecular subtyping has been widely used to dissect inter-tumor biological heterogeneity, in relation to clinical outcomes. A key step of this methodology is to perform unsupervised classification of gene expression profiles, which, however, often suffers challenges of high-dimensionality, feature redundancy as well as noise and irrelevant information. To overcome these limitations, we propose ELM-CC, which employs hidden observation features obtained from extreme learning machines (ELMs) for cancer classification. To demonstrate the effectiveness and usefulness, we applied ELM-CC for gastric and ovarian cancer subtyping. Comparing with the widely-used consensus clustering method, our approach demonstrated much better clustering performance and identified molecular subtypes that are much more clinically relevant. [ABSTRACT FROM AUTHOR]

The ability to predict what courses a student may enroll in the coming semester plays a pivotal role in the allocation of learning resources, which is a hot topic in the domain of educational data mining. In this study, we propose an innovative approach to characterize students’ cross-college course enrollments by leveraging a novel contextual graph. Specifically, different kinds of variables, such as students, courses, colleges and diplomas, as well as various types of variable relations, are utilized to depict the context of each variable, and then a representation learning algorithm node2vec is applied to extracting sophisticated graph-based features for the enrollment analysis. In this manner, the relations between any pair of variables can be measured quantitatively, which enables the variable type to transform from nominal to ratio. These graph-based features are examined by the random forest algorithm, and experiments on 24,663 students, 1,674 courses and 417,590 enrollment records demonstrate that the contextual graph can successfully improve analyzing the cross-college course enrollments, where three of the graph-based features have significantly stronger impacts on prediction accuracy than the others. Besides, the empirical results also indicate that the student’s course preference is the most important factor in predicting future course enrollments, which is consistent to the previous studies that acknowledge the course interest is a key point for course recommendations. [ABSTRACT FROM AUTHOR]

Despite the growing interest in prediction-based word embedding learning methods, it remains unclear as to how the vector spaces learnt by the prediction-based methods differ from that of the counting-based methods, or whether one can be transformed into the other. To study the relationship between counting-based and prediction-based embeddings, we propose a method for learning a linear transformation between two given sets of word embeddings. Our proposal contributes to the word embedding learning research in three ways: (a) we propose an efficient method to learn a linear transformation between two sets of word embeddings, (b) using the transformation learnt in (a), we empirically show that it is possible to predict distributed word embeddings for novel unseen words, and (c) empirically it is possible to linearly transform counting-based embeddings to prediction-based embeddings, for frequent words, different POS categories, and varying degrees of ambiguities. [ABSTRACT FROM AUTHOR]

This study examined predictors of the development of Wikipedia articles that deal with controversial issues. We chose a corpus of articles in the German-language version of Wikipedia about alternative medicine as a representative controversial issue. We extracted edits made until March 2013 and categorized them using a supervised machine learning setup as either being pro conventional medicine, pro alternative medicine, or neutral. Based on these categories, we established relevant variables, such as the perspectives of articles and of authors at certain points in time, the (im)balance of an article’s perspective, the number of non-neutral edits per article, the number of authors per article, authors’ heterogeneity per article, and incongruity between authors’ and articles’ perspectives. The underlying objective was to predict the development of articles’ perspectives with regard to the controversial topic. The empirical part of the study is embedded in theoretical considerations about editorial biases and the effectiveness of norms and rules in Wikipedia, such as the neutral point of view policy. Our findings revealed a selection bias where authors edited mainly articles with perspectives similar to their own viewpoint. Regression analyses showed that an author’s perspective as well as the article’s previous perspectives predicted the perspective of the resulting edits, albeit both predictors interact with each other. Further analyses indicated that articles with more non-neutral edits were altogether more balanced. We also found a positive effect of the number of authors and of the authors’ heterogeneity on articles’ balance. However, while the effect of the number of authors was reserved to pro-conventional medicine articles, the authors’ heterogenity effect was restricted to pro-alternative medicine articles. Finally, we found a negative effect of incongruity between authors’ and articles’ perspectives that was pronounced for the pro-alternative medicine articles. [ABSTRACT FROM AUTHOR]

Building on developments in machine learning and prior work in the science of judicial prediction, we construct a model designed to predict the behavior of the Supreme Court of the United States in a generalized, out-of-sample context. To do so, we develop a time-evolving random forest classifier that leverages unique feature engineering to predict more than 240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015). Using only data available prior to decision, our model outperforms null (baseline) models at both the justice and case level under both parametric and non-parametric tests. Over nearly two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the justice vote level. More recently, over the past century, we outperform an in-sample optimized null model by nearly 5%. Our performance is consistent with, and improves on the general level of prediction demonstrated by prior work; however, our model is distinctive because it can be applied out-of-sample to the entire past and future of the Court, not a single term. Our results represent an important advance for the science of quantitative legal prediction and portend a range of other potential applications. [ABSTRACT FROM AUTHOR]

There are several methods for building prediction models. The wealth of currently available modeling techniques usually forces the researcher to judge, a priori, what will likely be the best method. Super learning (SL) is a methodology that facilitates this decision by combining all identified prediction algorithms pertinent for a particular prediction problem. SL generates a final model that is at least as good as any of the other models considered for predicting the outcome. The overarching aim of this work is to introduce SL to analysts and practitioners. This work compares the performance of logistic regression, penalized regression, random forests, deep learning neural networks, and SL to predict successful substance use disorders (SUD) treatment. A nationwide database including 99,013 SUD treatment patients was used. All algorithms were evaluated using the area under the receiver operating characteristic curve (AUC) in a test sample that was not included in the training sample used to fit the prediction models. AUC for the models ranged between 0.793 and 0.820. SL was superior to all but one of the algorithms compared. An explanation of SL steps is provided. SL is the first step in targeted learning, an analytic framework that yields double robust effect estimation and inference with fewer assumptions than the usual parametric methods. Different aspects of SL depending on the context, its function within the targeted learning framework, and the benefits of this methodology in the addiction field are discussed. [ABSTRACT FROM AUTHOR]

Missing data is a common problem in many research fields and is a challenge that always needs careful considerations. One approach is to impute the missing values, i.e., replace missing values with estimates. When imputation is applied, it is typically applied to all records with missing values indiscriminately. We note that the effects of imputation can be strongly dependent on what is missing. To help make decisions about which records should be imputed, we propose to use a machine learning approach to estimate the imputation error for each case with missing data. The method is thought to be a practical approach to help users using imputation after the informed choice to impute the missing data has been made. To do this all patterns of missing values are simulated in all complete cases, enabling calculation of the “true error” in each of these new cases. The error is then estimated for each case with missing values by weighing the “true errors” by similarity. The method can also be used to test the performance of different imputation methods. A universal numerical threshold of acceptable error cannot be set since this will differ according to the data, research question, and analysis method. The effect of threshold can be estimated using the complete cases. The user can set an a priori relevant threshold for what is acceptable or use cross validation with the final analysis to choose the threshold. The choice can be presented along with argumentation for the choice rather than holding to conventions that might not be warranted in the specific dataset. [ABSTRACT FROM AUTHOR]

A computational procedure to search for selective ligands for structurally related protein targets was developed and verified for serotonergic 5-HT7/5-HT1A receptor ligands. Starting from a set of compounds with annotated activity at both targets (grouped into four classes according to their activity: selective toward each target, not-selective and not-selective but active) and with an additional set of decoys (prepared using DUD methodology), the SVM (Support Vector Machines) models were constructed using a selective subset as positive examples and four remaining classes as negative training examples. Based on these four component models, the consensus classifier was then constructed using a data fusion approach. The combination of two approaches of data representation (molecular fingerprints vs. structural interaction fingerprints), different training set sizes and selection of the best SVM component models for consensus model generation, were evaluated to determine the optimal settings for the developed algorithm. The results showed that consensus models with molecular fingerprints, a larger training set and the selection of component models based on MCC maximization provided the best predictive performance. [ABSTRACT FROM AUTHOR]

In the business sector, it has always been a difficult task to predict the exact daily price of the stock market index; hence, there is a great deal of research being conducted regarding the prediction of the direction of stock price index movement. Many factors such as political events, general economic conditions, and traders’ expectations may have an influence on the stock market index. There are numerous research studies that use similar indicators to forecast the direction of the stock market index. In this study, we compare two basic types of input variables to predict the direction of the daily stock market index. The main contribution of this study is the ability to predict the direction of the next day’s price of the Japanese stock market index by using an optimized artificial neural network (ANN) model. To improve the prediction accuracy of the trend of the stock market index in the future, we optimize the ANN model using genetic algorithms (GA). We demonstrate and verify the predictability of stock price direction by using the hybrid GA-ANN model and then compare the performance with prior studies. Empirical results show that the Type 2 input variables can generate a higher forecast accuracy and that it is possible to enhance the performance of the optimized ANN model by selecting input variables appropriately. [ABSTRACT FROM AUTHOR]