A self-adaptive synthetic over-sampling technique for imbalanced classification

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50%-80%) is used for training and the rest—for validation. In many problems, however, the data are highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesizing feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesize data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesizing data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, for example, support vector machines, k-nearest neighbour classifiers deep neural, rule-based classifiers, decision trees, and so forth. The results demonstrated that (a) a significantly more balanced (and fair) classification results can be achieved and (b) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.     

Parameter tuning Naïve Bayes for automatic patent classification

I present an analysis of feature selection for automatic patent categorization. For a corpus of 7,309 patent applications from the World Patent Information (WPI) Test Collection (Lupu, 2019), I assign International Patent Classification (IPC) section codes using a modified Naïve Bayes classifier. I compare precision, recall, and f-measure for a variety of meta-parameter settings including data smoothing and acceptance threshold. Finally, I apply the optimized model to IPC class and group codes and compare the results of patent categorization to academic literature.     

油藏开发地质勘探的常见问题分析

就油藏开发地质勘探的常见问题进行分析,从油藏开发的分类、油藏开发程序以及油藏储量计算等方面综合考虑影响油藏开发的因素,为现实油藏开发工程提供理论依据,提升油藏开发技术水准。     

Geographical discrimination of honeys through antioxidant capacity,mineral content and colour

The assessment of geographical origin of honey is economically important for producers and consumers as every region may present particular quality characteristics. In this study, honeys from the seven different regions of Buenos Aires province (Argentina) were characterised by their antioxidant capacity (DPPH, FRAP), total phenolic content (TPC), mineral composition, colour and ash. Honeys showed significant differences among their antioxidant capacity (DPPH), ash, colour and mineral content (P ≤ 0.05). Besides, a good antioxidant activity and low amounts of Cu and Zn (<1.0–1.5 and 0.7–1.8 mg kg^?1, respectively) were found in the samples. Significant Pearson's correlations (P ≤ 0.05) among the different parameters were found. Moreover, the linear discriminant analysis allowed the classification of honeys in their original groups with a prediction success of 98%. The present results suggest that honeys could be correctly classified by their geographical origin through their TPC, colour, ash and mineral concentrations.     

Multiobjective PSO based adaption of neural network topology for pixel classification in satellite imagery

The proposed work involves the multiobjective PSO based adaption of optimal neural network topology for the classification of multispectral satellite images. It is per pixel supervised classification using spectral bands (original feature space). This paper also presents a thorough experimental analysis to investigate the behavior of neural network classifier for given problem. Based on 1050 number of experiments, we conclude that following two critical issues needs to be addressed: (1) selection of most discriminative spectral bands and (2) determination of optimal number of nodes in hidden layer. We propose new methodology based on multiobjective particle swarm optimization (MOPSO) technique to determine discriminative spectral bands and the number of hidden layer node simultaneously. The accuracy with neural network structure thus obtained is compared with that of traditional classifiers like MLC and Euclidean classifier. The performance of proposed classifier is evaluated quantitatively using Xie-Beni and β indexes. The result shows the superiority of the proposed method to the conventional one.     

Mining citizen emotions to estimate the urgency of urban issues

Crowdsourcing technology offers exciting possibilities for local governments. Specifically, citizens are increasingly taking part in reporting and discussing issues related to their neighborhood and problems they encounter on a daily basis, such as overflowing trash-bins, broken footpaths and lifts, illegal graffiti, and potholes. Pervasive citizen participation enables local governments to respond more efficiently to these urban issues. This interaction between citizens and municipalities is largely promoted by civic engagement platforms, such as See-Click-Fix, FixMyStreet, CitySourced, and OpenIDEO, which allow citizens to report urban issues by entering free text describing what needs to be done, fixed or changed. In order to develop appropriate action plans and priorities, government officials need to figure out how urgent are the reported issues. In this paper we propose to estimate the urgency of urban issues by mining different emotions that are implicit in the text describing the issue. More specifically, a reported issue is first categorized according to the emotions expressed in it, and then the corresponding emotion scores are combined in order to produce a final urgency level for the reported issue. Our experiments use the SeeClickFix hackathon data and diverse emotion classification algorithms. They indicate that (i) emotions can be categorized efficiently with supervised learning algorithms, and (ii) the use of citizen emotions leads to accurate urgency estimates. Further, using additional features such as the type of issue or its author leads to no further accuracy gains.     

Improved 3D image segmentation for X-ray tomographic analysis of packed particle beds

Although High Resolution X-ray Micro Tomography (HRXMT) has been developed in the past years for the 3D analysis of multiphase mineral particles in packed particle beds, image analysis of fine and/or high-density/high atomic number particles has been limited by existing segmentation algorithms. In this regard, a feature-based segmentation algorithm has been developed and demonstrated to provide a more accurate image processing method for the analysis of such multiphase particle populations. Based on this improved segmentation algorithm, image analyses of packed particle bed samples were compared to segmentation by traditional 3D watershed segmentation. Also, calculation of particle number using optical microscopy, together with a digital camera, was accomplished to validate feature-based segmentation. Detailed procedures and results for sample preparation, image analysis and validation are presented and discussed.     

TCBR-HMM: An HMM-based text classifier with a CBR system

This paper presents an innovative solution to model distributed adaptive systems in biomedical environments. We present an original TCBR-HMM (Text Case Based Reasoning-Hidden Markov Model) for biomedical text classification based on document content. The main goal is to propose a more effective classifier than current methods in this environment where the model needs to be adapted to new documents in an iterative learning frame. To demonstrate its achievement, we include a set of experiments, which have been performed on OSHUMED corpus. Our classifier is compared with Naive Bayes and SVM techniques, commonly used in text classification tasks. The results suggest that the TCBR-HMM Model is indeed more suitable for document classification. The model is empirically and statistically comparable to the SVM classifier and outperforms it in terms of time efficiency.     

ECG heart beat classification method based on modified ABC algorithm

Electrocardiogram is the most commonly used tool for the diagnosis of cardiologic diseases. In order to help cardiologists to diagnose the arrhythmias automatically, new methods for automated, computer aided ECG analysis are being developed. In this paper, a Modified Artificial Bee Colony (MABC) algorithm for ECG heart beat classification is introduced. It is applied to ECG data set which is obtained from MITBIH database and the result of MABC is compared with seventeen other classifier's accuracy.In classification problem, some features have higher distinctiveness than others. In this study, in order to find higher distinctive features, a detailed analysis has been done on time domain features. By using the right features in MABC algorithm, high classification success rate (99.30%) is obtained. Other methods generally have high classification accuracy on examined data set, but they have relatively low or even poor sensitivities for some beat types. Different data sets, unbalanced sample numbers in different classes have effect on classification result. When a balanced data set is used, MABC provided the best result as 97.96% among all classifiers.Not only part of the records from examined MITBIH database, but also all data from selected records are used to be able to use developed algorithm on a real time system in the future by using additional software modules and making adaptation on a specific hardware.     

Spatially constrained sparse coding scheme for natural scene categorization

Coding and pooling, the major two sequential procedures in sparse coding based scene categorization systems, have drawn much attention in recent years. Yet improvements have been made for coding or pooling separately, this paper proposes a spatially constrained scheme for sparse coding on both steps. Specifically, we employ the m-nearest neighbors of a local feature in the image space to improve the consistency of coding. The benefit is that similar image features will be encoded with similar codewords, which reduced the stochasticity of a conventional coding strategy. We also show that the Viola–Jones algorithm, which is well-known in face detection, can be tailored to learning receptive fields, embedding the spatially constrained information on the pooling step. Extensive experiments on the UIUC sport event, 15 natural scenes and the Caltech 101 database suggests that scene categorization performance of several popular algorithms can be ubiquitously improved by incorporating the proposed two spatially constrained sparse coding scheme.