Search results

The purpose of this study is to show that closure-based classification and regression models provide both high accuracy and interpretability.

Pattern structures allow one to approach the knowledge extraction problem in case of partially ordered descriptions. They provide a way to apply techniques based on closed descriptions to non-binary data. To provide scalability of the approach, the author introduced a lazy (query-based) classification algorithm.

The experiments support the hypothesis that closure-based classification and regression allow one to both achieve higher accuracy in scoring models as compared to results obtained with classical banking models and retain interpretability of model results, whereas black-box methods grant better accuracy for the cost of losing interpretability.

This is an original research showing the advantage of closure-based classification and regression models in the banking sphere.

This work presents a system based on an ensemble of Convolutional Neural Networks (CNNs) and descriptors for bioimage classification that has been validated on different datasets of color images. The proposed system represents a very simple yet effective way of boosting the performance of trained CNNs by composing multiple CNNs into an ensemble and combining scores by sum rule. Several types of ensembles are considered, with different CNN topologies along with different learning parameter sets. The proposed system not only exhibits strong discriminative power but also generalizes well over multiple datasets thanks to the combination of multiple descriptors based on different feature types, both learned and handcrafted. Separate classifiers are trained for each descriptor, and the entire set of classifiers is combined by sum rule. Results show that the proposed system obtains state-of-the-art performance across four different bioimage and medical datasets. The MATLAB code of the descriptors will be available at https://github.com/LorisNanni.

The purpose of this paper is to develop a proof-of-concept (POC) Forward Collision Warning (FWC) system for the motorcyclist, which determines a potential clash based on time-to-collision and trajectory of both the detected and ego vehicle (motorcycle).

This comes in three approaches. First, time-to-collision value is to be calculated based on low-cost camera video input. Second, the trajectory of the detected vehicle is predicted based on video data in the 2 D pixel coordinate. Third, the trajectory of the ego vehicle is predicted via the lean direction of the motorcycle from a low-cost inertial measurement unit sensor.

This encompasses a comprehensive Advanced FWC system which is an amalgamation of the three approaches mentioned above. First, to predict time-to-collision, nested Kalman filter and vehicle detection is used to convert image pixel matrix to relative distance, velocity and time-to-collision data. Next, for trajectory prediction of detected vehicles, a few algorithms were compared, and it was found that long short-term memory performs the best on the data set. The last finding is that to determine the leaning direction of the ego vehicle, it is better to use lean angle measurement compared to riding pattern classification.

The value of this paper is that it provides a POC FWC system that considers time-to-collision and trajectory of both detected and ego vehicle (motorcycle).

The determinants of investors’ sentiment based on secondary stock market proxies in many empirical studies are reported. However, to the best of our knowledge, no study undertakes investor sentiment drivers developed from primary survey measures by constructing an investor sentiment index (ISI) in relation to market drivers to date. This study aims to fill this research gap by first developing the ISI for the Indian retail investors and then examining which of the stock market drivers impacts such sentiment.

The ISI is constructed using the mean scores of eight statements as formulated based on popular direct investor sentiment surveys undertaken across the world. Then, we use the multiple regression approach overall and for top 33.33% (high-sentiment) and bottom 33.33% (low-sentiment) investors based on the responses of 576 respondents on 18 statements (proxying eight study hypotheses) collected in 2016. Moreover, the demography-based classification based investors’ sentiment is examined to make our results more robust and in-depth.

On an overall basis, the IPO activities/issues and information certainty, trading volume and momentum and institutional investors’ investment activities market drivers significantly and positively impact retail investors is examined. However, only IPO activities/issues and information certainty influences both high- and low-sentiment investors. It is intriguing to report that nature of the stock markets show conflicting results for high- (negative significant) and low- (positive significant) sentiment investors.

The construction of the ISI from primary survey measure is for the first time in Indian context in relation to investigating the stock market drivers influential to retail investors’ sentiment. In addition, hypothesized market drivers are also unique, each representing different fundamental and technical characteristics associated with the Indian market.

The General Society Survey(GSS) is a kind of government-funded survey which aims at examining the Socio-economic status, quality of life, and structure of contemporary society. GSS data set is regarded as one of the authoritative source for the government and organization practitioners to make data-driven policies. The previous analytic approaches for GSS data set are designed by combining expert knowledges and simple statistics. By utilizing the emerging data mining algorithms, we proposed a comprehensive data management and data mining approach for GSS data sets.

The approach are designed to be operated in a two-phase manner: a data management phase which can improve the quality of GSS data by performing attribute pre-processing and filter-based attribute selection; a data mining phase which can extract hidden knowledge from the data set by performing data mining analysis including prediction analysis, classification analysis, association analysis and clustering analysis.

According to experimental evaluation results, the paper have the following findings: Performing attribute selection on GSS data set can increase the performance of both classification analysis and clustering analysis; all the data mining analysis can effectively extract hidden knowledge from the GSS data set; the knowledge generated by different data mining analysis can somehow cross-validate each other.

By leveraging the power of data mining techniques, the proposed approach can explore knowledge in a fine-grained manner with minimum human interference. Experiments on Chinese General Social Survey data set are conducted at the end to evaluate the performance of our approach.

Automatic anatomical therapeutic chemical (ATC) classification is progressing at a rapid pace because of its potential in drug development. Predicting an unknown compound's therapeutic and chemical characteristics in terms of how it affects multiple organs and physiological systems makes automatic ATC classification a vital yet challenging multilabel problem. The aim of this paper is to experimentally derive an ensemble of different feature descriptors and classifiers for ATC classification that outperforms the state-of-the-art.

The proposed method is an ensemble generated by the fusion of neural networks (i.e. a tabular model and long short-term memory networks (LSTM)) and multilabel classifiers based on multiple linear regression (hMuLab). All classifiers are trained on three sets of descriptors. Features extracted from the trained LSTMs are also fed into hMuLab. Evaluations of ensembles are compared on a benchmark data set of 3883 ATC-coded pharmaceuticals taken from KEGG, a publicly available drug databank.

Experiments demonstrate the power of the authors’ best ensemble, EnsATC, which is shown to outperform the best methods reported in the literature, including the state-of-the-art developed by the fast.ai research group. The MATLAB source code of the authors’ system is freely available to the public at https://github.com/LorisNanni/Neural-networks-for-anatomical-therapeutic-chemical-ATC-classification.

This study demonstrates the power of extracting LSTM features and combining them with ATC descriptors in ensembles for ATC classification.

This study aimed to assess the potential of the Clinical Dementia Rating (CDR) Scale in the prognosis of dementia in elderly subjects.

Dementia staging severity is clinically an essential task, so the authors used machine learning (ML) on the magnetic resonance imaging (MRI) features to locate and study the impact of various MR readings onto the classification of demented and nondemented patients. The authors used cross-sectional MRI data in this study. The designed ML approach established the role of CDR in the prognosis of inflicted and normal patients. Moreover, the pattern analysis indicated CDR as a strong cohort amongst the various attributes, with CDR to have a significant value of p < 0.01. The authors employed 20 ML classifiers.

The mean prediction accuracy varied with the various ML classifier used, with the bagging classifier (random forest as a base estimator) achieving the highest (93.67%). A series of ML analyses demonstrated that the model including the CDR score had better prediction accuracy and other related performance metrics.

The results suggest that the CDR score, a simple clinical measure, can be used in real community settings. It can be used to predict dementia progression with ML modeling.

Classifying moving objects in video sequences has been extensively studied, yet it is still an ongoing problem. In this paper, we propose to solve moving objects classification problem via an extended version of two-dimensional principal component analysis (2DPCA), named as category-wise 2DPCA (CW2DPCA). A key component of the CW2DPCA is to independently construct optimal projection matrices from object-specific training datasets and produce category-wise feature spaces, wherein each feature space uniquely captures the invariant characteristics of the underlying intra-category samples. Consequently, on one hand, CW2DPCA enables early separation among the different object categories and, on the other hand, extracts effective discriminative features for representing both training datasets and test objects samples in the classification model, which is a nearest neighbor classifier. For ease of exposition, we consider human/vehicle classification, although the proposed CW2DPCA-based classification framework can be easily generalized to handle multiple objects classification. The experimental results prove the effectiveness of CW2DPCA features in discriminating between humans and vehicles in two publicly available video datasets.

Classification techniques have been applied to many applications in various fields of sciences. There are several ways of evaluating classification algorithms. The analysis of such metrics and its significance must be interpreted correctly for evaluating different learning algorithms. Most of these measures are scalar metrics and some of them are graphical methods. This paper introduces a detailed overview of the classification assessment measures with the aim of providing the basics of these measures and to show how it works to serve as a comprehensive source for researchers who are interested in this field. This overview starts by highlighting the definition of the confusion matrix in binary and multi-class classification problems. Many classification measures are also explained in details, and the influence of balanced and imbalanced data on each metric is presented. An illustrative example is introduced to show (1) how to calculate these measures in binary and multi-class classification problems, and (2) the robustness of some measures against balanced and imbalanced data. Moreover, some graphical measures such as Receiver operating characteristics (ROC), Precision-Recall, and Detection error trade-off (DET) curves are presented with details. Additionally, in a step-by-step approach, different numerical examples are demonstrated to explain the preprocessing steps of plotting ROC, PR, and DET curves.