Set Of Primary Features Research Articles

Фразеологізація інтернет-мемів

The article analyzes modern Internet memes, which, due to their precedent, are able to be phraseologized in mass communication. Memes are considered intertextual polycode units that arise as a verbalized reflection on the dynamic development of events and actively function in the virtual media space. It has been proven that the language of Internet memes is built on irony and sarcasm using stylistic puns and "word games", oxymorons and gradation techniques, as well as aphorisms, precedent quotes, established constructions. A special emphasis is placed on war memes, which are characterized, in our opinion, by a set of primary features: (a) a catchy word, expression, verbal / non-verbal sign must be precedents; (b) spontaneity in appearance; (c) flexibility to modifications in order to interpret different events and phenomena; (d) appeal to the background knowledge of recipients; (e) semantic unity in form and content; (e) reproduction of cultural memory and response to the digital challenges of modernity. All this enables Internet memes in language communication to phraseologize and be able to be widely replicated in the information space. It is emphasized that communicators can independently create Internet memes and distribute them on their own media resources, which emphasizes the ability of memes to be constantly modified. For illustrative material, we turned to the information of the "Ukrainian Cultural Heritage Online" (SUCHO) portal, which has more than 10,000 memes as cultural markers of Ukraine. Having analyzed the memes of 2023, we can state that most Internet memes are precedent phenomena of the modern media space, and therefore have the ability to phraseologize. Therefore, Internet memes are a powerful source of new phraseology, have the ability to stylistically transform and help to strengthen the impression of a relevant informational message.

Inadequacy of Evolutionary Profiles Vis-a-vis Single Sequences in Predicting Transient DNA-Binding Sites in Proteins

Sequence-based prediction of DNA-binding residues in a protein is a widely studied problem for which machine learning methods with continuously improving predictive power have been developed. Concatenated rows within a sliding window of a Position Specific Substitution Matrix (PSSM) of the protein are currently used as the primary feature set in almost all the methods of predicting DNA-binding residues. Here we report that these evolutionary profiles are powerful, only for identifying conserved binding sites and fall short for the residue positions which undergo binding to non-binding transitions in closely related proteins. We created a database of highly similar protein pairs with known protein-DNA complexes and investigated differential predictability of conserved and transient binding residues within each pair. Retraining machine learning models uniformly, we compared the predictive powers of the models trained on PSSMs against similarly trained models on sparse-encoded single sequences. We found that the transient binding site predictions from evolutionary profiles are outperformed by single-sequence based models under controlled experiments by as much as 8 percentage points. Thus, we conclude that the PSSM-based models are inadequate to predict high-specificity DNA-binding residues. These findings are of critical significance for the design of mutant- and species-specific DNA ligands and for homology based modeling of protein-DNA complexes.

Intelligent Prediction Mathematical Model of Industrial Financial Fraud Based on Data Mining

The essence of enterprise financial modeling is to use mathematical models to classify and sort out all kinds of enterprise information according to the main line of value creation and on this basis to complete the analysis, prediction, and value evaluation of enterprise financial situation. A reasonable financial model is also an effective means to reduce financial fraud. In this paper, a financial fraud identification model is constructed based on empirical data. In the process of model construction, the primary feature set is selected according to the financial fraud motivation theory, and then, the original feature set is obtained by Mann–Whitney test on the primary feature set, and the final fraud identification feature set is selected from the original feature set by using Relief and Boruta algorithms. Finally, based on the final fraud identification feature set, the data algorithms such as decision tree, logistic regression, support vector machine, and random forest are used to identify financial fraud. The experimental results show that the combination of financial fraud identification features constructed by the Relief algorithm and random forest model has the best recognition effect. The evaluation indexes of the G mean value and the F value were 75.86% and 78.33%, respectively.

A robust digital watermarking technique based on feature and transform method

This paper proposed a new robust digital watermarking technique with an aim of image protection. The proposed technique incorporates both the transform and feature methods. Initially, the Harris Laplacian detector extracts the features from the cover image that suites well for the watermarking. The extracted characteristic regions are grouped to form a primary feature set where the secret message is embedded to form a watermarked image. This image is tested by introducing six different predefined attacks, which checks the robustness of the extracted feature.Discrete cosine transform (DCT) transformation method extracts the secret message from the watermarked image. According to the results, the watermarked image is vulnerable to the undefined attack. To enhance the resistance against those attacks the primary feature set is extended by adding some auxiliary features. These features are extracted through Knapsack algorithm. The watermark is embedded into these auxiliary features where the secret message is not affected by any attacks. The experimental results show that the proposed watermark technique is efficient and also preserves the image quality. Key words: Feature detector, Knapsack algorithm, watermark protection, attack resistant, digital watermarking.

Selection of Feature Regions Set for Digital Image Using Optimization Algorithm

Image transformation techniques are used for extraction of local features which are used in many applications such as object recognition, database retrieval, and motion tracking. The effectiveness of a digital image is identified by the robustness of image candidate regions. This paper aims to obtain most robust and minimal region set which preserves image quality. It first performs a simulated attacking procedure on non overlapped region set to evaluate the robustness of every candidate feature region. According to the evaluation results, it then adopts a track-with-pruning procedure to search a minimal primary feature set which can resist the most predefined attacks. In order to enhance its resistance to undefined attacks under the constraint of preserving image quality, the primary feature set is then extended by adding into some auxiliary feature regions. This work is formulated as a multidimensional knapsack problem and would be solved by Optimization Algorithms such as Genetic Algorithm as well as Particle Swarm Optimization and Simulated Annealing based approach. The experimental result uses some benchmark images. Comparing results of different optimization techniques on primary feature region set, the proposed method determines the best choice of optimization techniques for selecting most robust and minimal region set under the constraint of preserving image quality.

On the Selection of Optimal Feature Region Set for Robust Digital Image Watermarking

A novel feature region selection method for robust digital image watermarking is proposed in this paper. This method aims to select a nonoverlapping feature region set, which has the greatest robustness against various attacks and can preserve image quality as much as possible after watermarked. It first performs a simulated attacking procedure using some predefined attacks to evaluate the robustness of every candidate feature region. According to the evaluation results, it then adopts a track-with-pruning procedure to search a minimal primary feature set which can resist the most predefined attacks. In order to enhance its resistance to undefined attacks under the constraint of preserving image quality, the primary feature set is then extended by adding into some auxiliary feature regions. This work is formulated as a multidimensional knapsack problem and solved by a genetic algorithm based approach. The experimental results for StirMark attacks on some benchmark images support our expectation that the primary feature set can resist all the predefined attacks and its extension can enhance the robustness against undefined attacks. Comparing with some well-known feature-based methods, the proposed method exhibits better performance in robust digital watermarking.

Noise-tolerant electrocardiogram beat classification based on higher order statistics of subband components

This paper presents a noise-tolerant electrocardiogram (ECG) beat classification method based on higher order statistics (HOS) of subband components. Five levels of discrete wavelet transform (DWT) were applied to decompose the signal into six subband components. Higher order statistics proceeded to calculate four sets of HOS features from the three midband components, which together with three RR interval-related features constructed the primary feature set. A feature selection algorithm based on correlation coefficient and Fisher discriminality was then exploited to eliminate redundant features from the primary feature set. A feedforward backpropagation neural network (FFBNN) was employed as the classifier. Two sample selection strategies and four categories of noise artifacts were utilized to justify the capacity of the method. More than 97.5% discrimination rate was achieved, no matter which of the two sampling selection strategies was used. By using the feature selection method, the feature dimension can be readily reduced from 30 to 18 with negligible decrease in accuracy. Compared with other method in the literature, the proposed method improves the sensitivities of most beat types, resulting in an elevated average accuracy. The proposed method is tolerant to environmental noises; as high as 91% accuracies were retained even when contaminated with serious noises, 10 dB signal-to-noise ration (SNR), of different kinds. The results demonstrate the effectiveness and noise-tolerant capacities of the proposed method in ECG beat classification.

A new approach for EEG feature extraction in P300-based lie detection

P300-based Guilty Knowledge Test (GKT) has been suggested as an alternative approach for conventional polygraphy. The purpose of this study was to extend a previously introduced pattern recognition method for the ERP assessment in this application. This extension was done by the further extending the feature set and also the employing a method for the selection of optimal features. For the evaluation of the method, several subjects went through the designed GKT paradigm and their respective brain signals were recorded. Next, a P300 detection approach based on some features and a statistical classifier was implemented. The optimal feature set was selected using a genetic algorithm from a primary feature set including some morphological, frequency and wavelet features and was used for the classification of the data. The rates of correct detection in guilty and innocent subjects were 86%, which was better than other previously used methods.

Machining process planning of prismatic parts using case-based reasoning and past process knowledge

A process planner for three-dimension prismatic parts is developed in this paper by utilizing case-based techniques. A three-dimension prismatic part is represented by a set of primary features (such as holes, pockets, slots, etc). The subplan candidates for individual features of a part are first generated by the proposed system via a backward inference planner based on the specifications of cutting tools available in a factory. The system then combines all subplans into the final process plan for a given part based on the merging information. The merging information is the information regarding the manufacturing environment of a factory (i.e. machine layout, transfer line, etc), and plays a key role in the process planning. Generally, the merging information is contained in old plans, and will be extracted by the system using case-based techniques. This way, the proposed system can generate a practical process plan for a given part based on case histories provided by the factory itself. The proposed process planner is composed of five major components: feature indexer, retriever, modifier, simulator, and repairer. It is implemented on a Sun workstation using the ACIS geometric modeler and C++ .