Data Classification Algorithms Research Articles

Analysis and Synthesis of Technology for Textual Information Classification

The task of developing effective text information classification systems requires the thoughtful analysis and synthesis of variable components of technology. These components strongly affect the practical efficiency and the requirements to the data. For this purpose, a typical technology was discussed, comparing the regular “learning from features” approach versus the more advanced “deep learning” approach, that studies from data. In order to implement the technology, the first approach was tested, which included the means (methods, algorithms) for analysis of the features of the source text, by applying the dimensionality transformation, and building model solutions that allow the correct classification of data by a set of features. As a result, all the steps of the technology are described, which allowed to determine the way of presenting data in terms of hidden features in data, their presentation in a standard visual form and evaluate the solution, as well as its practical efficiency, based on this set of features. In a depth study, the informational core of the document was studied, using the regression and T-stochastic grouping of features for dimensionality reduction.The separate results contain estimation of practical efficiency of the algorithms in terms of time and relative performance for each step of the proposed technology. This estimation gives a possibility to obtain the best algorithm of intelligent data processing that is useful for a given dataset and application. In order to estimate the best suited algorithm for separation in reduced dimension an experiment was carried out which allowed the selection of the best range of data classification algorithms, in particular boosting methods. As a result of the analysis of the technology, the necessary steps of this technology were discussed and the classification on real text data was conducted, which allowed to identify the most important stages of the technology for text classification.

A Novel Bioinspired Algorithm for Mixed and Incomplete Breast Cancer Data Classification.

The pre-diagnosis of cancer has been approached from various perspectives, so it is imperative to continue improving classification algorithms to achieve early diagnosis of the disease and improve patient survival. In the medical field, there are data that, for various reasons, are lost. There are also datasets that mix numerical and categorical values. Very few algorithms classify datasets with such characteristics. Therefore, this study proposes the modification of an existing algorithm for the classification of cancer. The said algorithm showed excellent results compared with classical classification algorithms. The AISAC-MMD (Mixed and Missing Data) is based on the AISAC and was modified to work with datasets with missing and mixed values. It showed significantly better performance than bio-inspired or classical classification algorithms. Statistical analysis established that the AISAC-MMD significantly outperformed the Nearest Neighbor, C4.5, Naïve Bayes, ALVOT, Naïve Associative Classifier, AIRS1, Immunos1, and CLONALG algorithms in conducting breast cancer classification.

Network Optimization based on Genetic Algorithm for High-Level Data Classification

High-level data classification techniques are capable of considering not only physical aspects of the data, such as space, distance, proximity, distribution, but can also consider their functional, topological and structural aspects. High-level techniques are commonly defined in two major steps: the construction of a network from the feature vector data and the uncovering of its underlying patterns using complex networks properties. In the network construction step, heuristics based on k-nearest neighbors strategies have been widely adopted, while several complex network measures (e.g. PageRank) have been modeled to learn high-level patterns of the input data. As both steps are directly related, i.e., the network configuration impacts directly the results obtained by the classifier, in this paper we develop a genetic algorithm (GA) to optimize the network construction step. To be specific, we hypothesize that the salient features of GAs, such as their robust search mechanism and binary representation, may provide a more powerful network representation in the context of the high-level classification based on importance characterization. In summary, extensive experiments with real data sets demonstrate that the networks provided by our GA strategy achieved higher predictive accuracy than those of a widely adopted method based on the nearest neighbors heuristic and competitive results against state-of-the-art ones.

A hybrid approach based on mathematical modelling and improved online learning algorithm for data classification

This paper proposes a novel hybrid classifier method using a mixed-integer linear programming (MILP) model and an improved online learning algorithm for general fuzzy min–max neural networks (IOL_GFMM). IOL_GFMM is used to generate initial hyper-boxes for the MILP model in order to improve its efficiency. This paper is the first attempt that integrates the fuzzy min–max neural networks and the MILP model. The applicability of the proposed hybrid model is proven on both real and artificial datasets. Performance evaluation parameters of the novel hybrid classifier are classification accuracy, training time, number of iterations, and number of misclassified data. Results show that the proposed hybrid method provides satisfying improvements in performance evaluation parameters compared with the pure MILP model. Our proposed approach achieves to speed the training time up to 76 times and decreases the number of misclassified data by up to 17 times. Results of artificial datasets show another contribution that the proposed hybrid approach is very efficient in order to classify data samples not only when they belong to separate regions but also when there exists significant overlap.

Memetic micro-genetic algorithms for cancer data classification

Fast and precise medical diagnosis of human cancer is crucial for treatment decisions. Gene selection consists of identifying a set of informative genes from microarray data to allow high predictive accuracy in human cancer classification. This task is a combinatorial search problem, and optimisation methods can be applied for its resolution. In this paper, two memetic micro-genetic algorithms (MμV1 and MμV2) with different hybridisation approaches are proposed for feature selection of cancer microarray data. Seven gene expression datasets are used for experimentation. The comparison with stochastic state-of-the-art optimisation techniques concludes that problem-dependent local search methods combined with micro-genetic algorithms improve feature selection of cancer microarray data.

A Feature Selection Approach Based on Archimedes’ Optimization Algorithm for Optimal Data Classification

A Feature Selection Approach Based on Archimedes’ Optimization Algorithm for Optimal Data Classification

Multi label attribute classification algorithm for big data based on core density estimation

Multi label attribute classification algorithm for big data based on core density estimation

High performance clean versus artifact dry electrode EEG data classification using Convolutional Neural Network transfer learning

ObjectiveConvolutional Neural Networks (CNNs) are promising for artifact detection in electroencephalography (EEG) data, but require large amounts of data. Despite increasing use of dry electrodes for EEG data acquisition, dry electrode EEG datasets are sparse. We aim to develop an algorithm for clean versus artifact dry electrode EEG data classification using transfer learning. MethodsDry electrode EEG data were acquired in 13 subjects while physiological and technical artifacts were induced. Data were per 2-second segment labeled as clean or artifact and split in an 80% train and 20% test set. With the train set, we fine-tuned a pre-trained CNN for clean versus artifact wet electrode EEG data classification using 3-fold cross validation. The three fine-tuned CNNs were combined in one final clean versus artifact classification algorithm, in which the majority vote was used for classification. We calculated accuracy, F1-score, precision, and recall of the pre-trained CNN and fine-tuned algorithm when applied to unseen test data. ResultsThe algorithm was trained on 0.40 million and tested on 0.17 million overlapping EEG segments. The pre-trained CNN had a test accuracy of 65.6%. The fine-tuned clean versus artifact classification algorithm had an improved test accuracy of 90.7%, F1-score of 90.2%, precision of 89.1% and recall of 91.2%. ConclusionsDespite a relatively small dry electrode EEG dataset, transfer learning enabled development of a high performing CNN-based algorithm for clean versus artifact classification. SignificanceDevelopment of CNNs for classification of dry electrode EEG data is challenging as dry electrode EEG datasets are sparse. Here, we show that transfer learning can be used to overcome this problem.

A Combined Priori and Purity Gaussian OverSampling Algorithm for Imbalanced Data Classification

A Combined Priori and Purity Gaussian OverSampling Algorithm for Imbalanced Data Classification

An Oscillator-Synchronization-Based Off-Line Learning Algorithm, With On-Chip Inference on an Array of Spin Hall Nano-Oscillators

Learning algorithms based on synchronization of oscillators are currently being pursued as an alternative to standard neural-network algorithms for data classification. For such oscillator-based algorithms, while learning can be implemented off-line on a computer, on-chip inference/ testing can be implemented on an array of uniform-mode spin Hall nano-oscillators (SHNOs), leading to a scalable and energy-efficient technology. Here, we propose a modification to an existing oscillator-based off-line learning algorithm for binary classification: unlike in the previous version of the algorithm, here the difference between natural frequencies of the output oscillators is kept constant throughout the learning process. This helps in preservation of the shape of the synchronization region and leads to higher classification accuracy, as we show for binary-classification tasks using two popular data sets: Fisher's Iris and MNIST. Next, in this paper, we show how a synchronization pattern obtained after such training, using our proposed algorithm, can be implemented on an array of dipole-coupled uniform-mode SHNOs for on-chip inference. We model the SHNO system through the macro-spin model, which is computationally much less resource-intensive to simulate compared to the micromagnetic model used previously for this kind of study. We also extend our algorithm to multi-class classification and thereby discuss scaling of our system.

CSEA: A Fine-Grained Framework of Climate-Season-Based Energy-Aware in Cloud Storage Systems

Abstract Continuous data scale growth increases energy consumption and operating cost that cannot be ignored in cloud storage systems. Previous studies have shown that analyzing the characteristics of I/O access and mining data features is effective for reasonable data distribution in storage systems. The granularity and criterion of classification are the key factors in determining the data distribution. To decrease energy consumption and operating cost, this paper puts forward a fine-grained framework of the climatic-season-based energy-aware in cloud storage system called CSEA. The framework concludes the following three aspects: (i) data feature mining. CSEA discovers potential data features by analyzing data access to provide help with data classification. (ii) K-means clustering algorithm. CSEA uses an unsupervised data classification algorithm in machine learning to divide data into categories based on seasonal characteristics by gathering real I/O access. (iii) data distribution of fine-grained. On the basis of seasonal features, CSEA fuses regional features to further refine the data distribution granularity to save on energy consumption and operating cost. Simulation experiments using extended CloudSimDisk and the constructed mathematical models indicate that CSEA reduces the energy consumption and operating cost compared with the single data classification standard and coarse-grained data distribution.

Sentiment Analysis of Indonesian Interest in Korean Food Based on Naïve Bayes Algorithm

Most Korean (South Korean) cultural products, such as drama films, songs, fashion,and food, are rising worldwide. The Korean Wave or Hallyu phenomenon shows howKorean culture is accepted by people all over the world. Social media has piqued theinterest of Indonesians, particularly young people, in Korean culture. The phenomenoncreates new business, especially for Korean food. Many Indonesians are curious totry the food after watching Korean Dramas or Korean artists on social media. Thepurpose of this study is to explore Indonesians’ perspective on Korean food throughsocial media platforms such as Twitter and YouTube. This research measures sentimentanalysis from an Indonesian perspective. The method uses the Naive Bayes algorithmfor data classification. The results show that Korean food has generated positive andnegative interest in Indonesia. It means the opportunity to start a Korean food businessin Indonesia is widely open. As a result, developing a culinary business based on thethriving Korean culture may be a good opportunity.

An Improved Particle Swarm Optimization Algorithm for Data Classification

Optimisation-based methods are enormously used in the field of data classification. Particle Swarm Optimization (PSO) is a metaheuristic algorithm based on swarm intelligence, widely used to solve global optimisation problems throughout the real world. The main problem PSO faces is premature convergence due to lack of diversity, and it is usually stuck in local minima when dealing with complex real-world problems. In meta-heuristic algorithms, population initialisation is an important factor affecting population diversity and convergence speed. In this study, we propose an improved PSO algorithm variant that enhances convergence speed and population diversity by applying pseudo-random sequences and opposite rank inertia weights instead of using random distributions for initialisation. This paper also presents a novel initialisation population method using a quasi-random sequence (Faure) to create the initialisation of the swarm, and through the opposition-based method, an opposite swarm is generated. We proposed an opposition rank-based inertia weight approach to adjust the inertia weights of particles to increase the performance of the standard PSO. The proposed algorithm (ORIW-PSO-F) has been tested to optimise the weight of the feed-forward neural network for fifteen data sets taken from UCI. The proposed techniques’ experiment result depicts much better performance than other existing techniques.

PROTOMORPHISMS IN THE THEORY OF MARKOV ALGORITHMS AND BIG DATA OF SOCIO-ECONOMIC SYSTEMS

Protomorphisms known in category theory are investigated together with the theory of Markov algorithms. Protomorphisms are considered as an element extending the theoretical provisions of the theory of Markov algorithms. Protomorphisms are investigated in the big data of socio-economic systems in the tasks of countering money laundering and terrorist financing. Methods of assignment for protomorphisms of the absence of a preorder are considered. A synthesized method for recording protomorphism in a data cycle when entering input sample sets into a big data classification algorithm is considered. A method of writing a protomorphism using the alphabet M = λιτφп/αβδγχκμ for the N-scheme of the Markov algorithm is presented, by entering a new nonterminal symbol into it. Examples of protomorphisms in big data are considered. Protomorphisms are divided into those about the truth, which can be asked, and those for which it is impractical to make a judgment about truth or falsity. The Hempel paradox with protomorphisms is considered. For Hempel’s paradox with “classes”, the method of bringing the number of inductive observations to the total number of observations is specified. An example of filling an artificial intelligence database with protomorphism is considered. A practical example of the use of protomorphism in the task of countering money laundering and terrorist financing of the socio-economic system is given. It is shown that it is permissible to expand the alphabet M with new letters for some morphisms, separating them. It is concluded that in the task of countering money laundering and terrorist financing, it is advisable to use protomorphisms, since they can increase the level of completeness, reliability, and efficiency of the subsystem for countering money laundering and terrorist financing when making decisions.

Low-cost VIS/NIR range hand-held and portable photospectrometer and evaluation of machine learning algorithms for classification performance

In this study, the electronic design of a low-cost and portable spectrophotometer device capable of analyzing in the visible-near infrared region was established. The design of C#.NET-based user-friendly device control software and the development of machine learning algorithms for data classification as well as the comparison of the results were presented. When the spectrophotometer design and implementation studies are reviewed in the literature, two groups of subjects become prominent: (i) a new device fabrication, (ii) solution approaches to current problems by combining commercial portable spectrometer systems and devices with artificial intelligence applications. This work encompasses both groups, and a supportive approach has been followed on how to transform the theoretical knowledge into practice in device development and supportive software with the help of machine learning approaches from design to production. Three commercial spectral sensors, each with six photodiode arrays, were adopted in the spectrophotometer. Thus, 18 features belonging to each sample were acquired in the optical spectral region in the 410 nm to 940 nm band range. The spectral analyses were conducted with 9 different food types of powder or flake structures. A Support Vector Machines (SVM) and Convolutional Neural Network (CNN) approaches were employed for data classification. As a result, SVM and CNN achieved 97% and 95% accuracies, respectively. Moreover, we provided the spectral measurement data, the electronic circuit designs, the API files containing the artificial intelligence algorithms and the graphical user interface (GUI).

A Spark-Based Artificial Bee Colony Algorithm for Unbalanced Large Data Classification

With the rapid development of internet technology, the amount of collected or generated data has increased exponentially. The sheer volume, complexity, and unbalanced nature of this data pose a challenge to the scientific community to extract meaningful information from this data within a reasonable time. In this paper, we implemented a scalable design of an artificial bee colony for big data classification using Apache Spark. In addition, a new fitness function is proposed to handle unbalanced data. Two experiments were performed using the real unbalanced datasets to assess the performance and scalability of our proposed algorithm. The performance results reveal that our proposed fitness function can efficiently deal with unbalanced datasets and statistically outperforms the existing fitness function in terms of G-mean and F1-Score. In additon, the scalability results demonstrate that our proposed Spark-based design obtained outstanding speedup and scaleup results that are very close to optimal. In addition, our Spark-based design scales efficiently with increasing data size.

Dynamic just-in-time learning based model predictive control for variable pitch wind energy conversion system

The pitch adjustment is critical to maintain the stable operation of the wind energy conversion system (WECS) under high wind speed, which can reduce mechanical load and provide safe and reliable power input for the power grid. It makes the design of a pitch controller arduous because the WECS is the high order system with nonlinear, multi-variable, and strong coupling. Based on this, a novel pitch controller is presented by employing dynamic just-in-time learning (JITL) based model predictive control to investigate wind turbine performance in a high wind speed operating region. This method captures the wind power process nonlinearities by the set of local models available online via JITL technology. Moreover, in order to meet the requirements of the real-time operation of the wind power process, a three-dimensional space data classification algorithm is employed to classify the data by calculating the local density and the minimum distance. Furthermore, considering the multi-objective and strongly nonlinear optimal control characteristics of model predictive control, the proposed dynamic linear model is introduced into the design of the nonlinear wind power model predictive control system. The optimal control rate of the controller is determined by solving the convex optimization problem within the design framework. Finally, the feasibility and superiority of the strategy are demonstrated by a typical wind power process.

A Two-Stage Semi-Supervised High Maneuvering Target Trajectory Data Classification Algorithm

Labeled data in insufficient amounts and missing categories are two observable features for high maneuvering target trajectory data. However, the existing research achievements are insufficient for solving these two problems simultaneously during data classification. This study proposed a two-stage semi-supervised trajectory data classification algorithm. By pre-training the autoencoder and combining it with the Siamese network, a two-stage joint training was formed, which enabled the model to deal with missing categories by clustering and maintaining the classification ability under the missing label categories. The experimental simulation results showed that the performance of this algorithm was better than the classical semi-supervised algorithm label propagation and transferred learning when the amount of various labeled data was as low as 1–5. The two-stage training model also had a good effect on the problem of missing categories. When 75% of the types were missing, the purity could still reach 82%, which was about eight percentage points higher than the directly trained network. When two problems appeared simultaneously, compared with the directly trained network, the performance improved by about three percentage points on average, and the purity was consistently higher than the clustering results. In summary, this algorithm was more tolerant of the problems of labeled datasets, so it was more practical.

Comparison of the Social Welfare Data Classification Algorithm for Bantul Regency

Today, the main problem in the economy sector in Indonesia is related to poverty alleviation. In Bantul Regency, poverty alleviation relies on the poverty data. The Social Welfare Integrated Data set by the Ministry of Social Affairs of the Republic of Indonesia is currently can not describe the classification of the poverty. It is either the causes of the delay in handling the poverty problem in Bantul Regency. Mapping of the poverty data has a major impact to the accuracy of targets for poverty reduction programs. One of the mappings that can be do for the problems of poverty data is by using the classification method. With this classification, the poverty data can be classified into several groups according to their circumstances. These groups include the very poor, the poor, the vulnerable and the near poor. In this study, two classification methods will be tried, called Naive Bayes and K-nearest neighboor (KNN) to compare the best results based on a measurement method.

Work Readiness Prediction of Telkom University Students Using Multinomial Logistic Regression and Random Forest Method

Work readiness for college graduates is an essential and significant thing to get a job immediately after graduation. But what happens is that many graduates are unemployed after graduation or do not get jobs that match the majors they have studied for more than four years. Therefore, by using a people analytics approach, this study aims to predict the work readiness of Telkom University students and find out what factors affect student work-readiness after graduation. The model built is a multi-classes classification model. This model uses Chi-square Test calculation for feature selection, Multinomial Logistic Regression and Random Forest as a classification method, and confusion matrix as an evaluation method. Multinomial Logistic Regression is used because several studies use this algorithm for categorical data, while Random Forest is used to compare which model produces better accuracy. This study conducted several test scenarios, which obtained the best model by performing hyperparameter tuning and handling unbalanced data with SMOTE-ENN. Handling imbalanced data with SMOTE-ENN is used to improve accuracy scores and predict classes well, especially for minority class. The best accuracy of the Multinomial Logistic Regression method is 53.9%, and Random Forest is 48.5%.