Michal Prilepok

Medical Image Retrieval Using Vector Quantization and Fuzzy S-tree

The aim of the article is to present a novel method for fuzzy medical image retrieval (FMIR) using vector quantization (VQ) with fuzzy signatures in conjunction with fuzzy S-trees. In past times, a task of similar pictures searching was not based on searching for similar content (e.g. shapes, colour) of the pictures but on the picture name. There exist some methods for the same purpose, but there is still some space for development of more efficient methods. The proposed image retrieval system is used for finding similar images, in our case in the medical area – in mammography, in addition to the creation of the list of similar images – cases. The created list is used for assessing the nature of the finding – whether the medical finding is malignant or benign. The suggested method is compared to the method using Normalized Compression Distance (NCD) instead of fuzzy signatures and fuzzy S-tree. The method with NCD is useful for the creation of the list of similar cases for malignancy assessment, but it is not able to capture the area of interest in the image. The proposed method is going to be added to the complex decision support system to help to determine appropriate healthcare according to the experiences of similar, previous cases.

Text Similarity Based on Data Compression in Arabic

With the huge amount of online and offline written data, plagiarism detection has become an eminent need for various fields of science and knowledge. Various context based plagiarism detection methods have been published in the literature. This paper, tries to develop a new plagiarism detection methods using text similarity for Arabic language text with 150 documents and 330 paragraphs (159 from the source document and 171 from Al-Khaleej corpus). The findings of the study show that the similarity measurement based on Lempel Ziv comparison algorithms is very efficient for the plagiarized part of the Arabic text documents with a successful rate of 71.42%. Future studies can improve the efficiency of the algorithms by combining more sophisticated computation, statistical and linguistics hybrid detection methods.

Cattle Identification Using Muzzle Images

The quality of animal identification system plays an important role for producers to make management decisions about their herd or individual animals. The animal identification is also important to animal traceability systems to ensure the integrity of the food chain. Usually, recordings and readings of tags-based systems are used to identify an animal, but only effective in eradication programs of national disease. Recently, animal biometric-based solutions, e.g. muzzle imaging system, offer an effective and secure, and rapid method of addressing the requirements of animal identification and traceability systems. In this paper, we present an identification system based on muzzle images. The identification process is based on Support Vector Machine (SVM), Linear Discriminant Analysis (LDA) and Tucker Tensor Decomposition. This selected classifiers we compared on the same dataset of muzzle images with different experiment settings. The results we evaluated by F-score. The best F-score result gives us the Tucker Tensor Decomposition. It achieved the median of F-score 0.750.

Classification of EEG Signals Using Vector Quantization

Proper identification and classification of the EEG data still pauses a problem in the field of brain diagnosis. However, the application of such algorithm is almost unlimited as they may be involved in applications such as, brain computer interface for controlling of prosthesis, wheelchair, etc.. In this paper we are focusing on applying data compression in the classification of EEG signals. We combine a vector quantization and the normalized compression distance for proper classification of a finger movement data.

SPAM DETECTION USING DATA COMPRESSION AND SIGNATURES

In this article, we introduce a novel method for spam detection based on a combination of Bayesian filtering, signature trees, and data compression–based similarity. Bayesian filtering is one of the most popular and most efficient algorithms for dealing with spam detection. The problem with Bayesian filtering is that it is unable to classify any e-mail without doubt and sometimes spam e-mails are classified as regular e-mails. This novel method sorts out this problem by using signature trees and data compression–based similarity. The main result of this article is an up to 99% improvement in spam detection precision using this novel method.

Similarity Based on Data Compression

Similarity detection is one of the most important areas in document processing. The applications of it starts in spam detection and goes through identification of plagiarism in the web, bachelor or master thesis and ends at identification of copied scientific papers. This paper presents an improvement of a plagiarism detection algorithm which is based on the Lampel and Ziv dictionary based compression algorithm by application of stop words removing and tests this algorithm on real dataset. Moreover, a visualization of the plagiarized documents relationship is also presented. The algorithm confirms its ability in detection of the plagiarized parts of text and also the achieved improvement when the suggested improvements are applied.

Compression-based similarity in EEG signals

The electrical activity of brain or EEG signal is very complex data system that may be used to many different applications such as device control using mind. It is not easy to understand and detect useful signals in continuous EEG data stream. In this paper, we are describing an application of data compression which is able to recognize important patterns in this data. The proposed algorithm uses Lampel-Ziv complexity for complexity measurement and it is able to successfully detect patterns in EEG signal.

Spam detection using compression and PSO

The problem of spam emails is still growing. Therefore, developing of algorithms which are able to solve this problem is also very active area. This paper presents two different algorithms for spam detection. The first algorithm is based on Bayesian filter, but it is improved using data compression algorithms in case that the Bayesian filter cannot decide. The second algorithm is based on document classification algorithm using Particle Swarm Optimization. Results of presented algorithms are promising.

Utilizing Text Similarity Measurement for Data Compression to Detect Plagiarism in Czech

This paper attempts to apply data compression based similarity method for plagiarism detection. The method has been used earlier for plagiarism detection for Arabic and English languages. In this paper we utilize this method for Czech language text from a local multi-domain Czech corpus with 50 original documents with non-plagiarized parts, and 100 suspicious documents. The documents were generated so that every document could have from 1 to 5 paragraphs. The suspicion rate in the documents was randomly chosen from 0.2 to 0.8. The findings of the study show that the similarity measurement based on Lempel-Ziv comparison algorithms is efficient for the plagiarized part of the Czech text documents with a success rate of 82.60%. Future studies may enhance the efficiency of the algorithms by including combined and more sophisticated methods.

Evolutionary Weighted Ensemble for EEG Signal Recognition

Recognition of an EEG signal is a very complex but very important problem. In this paper we focus on a simplified classification problem which consists of detection finger movement based on an analysis of seven EEG sensors. The signals gathered by each sensor are subsequently classified by the respective classification algorithm, which is based on data compression and so called LZ-Complexity. To improve overall accuracy of the system, the Evolutionary Weighted Ensemble (EWE) system is proposed. The parameters of the EWE are set in a learning procedure which uses an evolutionary algorithm tailored for that purpose. To take full advantage of information returned by sensor classifiers, setting negative weights are permitted, which significantly raises overall accuracy. Evaluation of EWE and its comparison against selected traditional ensemble algorithm is carried out using empirical data consisting of almost 5 hundred samples. The results show that the EWE algorithm exploits the knowledge represented by the sensor classifiers very effectively, and greatly improves classification accuracy.