ECG-Based Identification of Sudden Cardiac Death through Sparse Representations

Sudden Cardiac Death (SCD) is an unexpected sudden death due to a loss of heart function and represents more than 50% of the deaths from cardiovascular diseases. Since cardiovascular problems change the features in the electrical signal of the heart, if significant changes are found with respect to a reference signal (healthy), then it is possible to indicate in advance a possible SCD occurrence. This work proposes SCD identification using Electrocardiogram (ECG) signals and a sparse representation technique. Moreover, the use of fixed feature ranking is avoided by considering a dictionary as a flexible set of features where each sparse representation could be seen as a dynamic feature extraction process. In this way, the involved features may differ within the dictionary’s margin of similarity, which is better-suited to the large number of variations that an ECG signal contains. The experiments were carried out using the ECG signals from the MIT/BIH-SCDH and the MIT/BIH-NSR databases. The results show that it is possible to achieve a detection 30 min before the SCD event occurs, reaching an an accuracy of 95.3% under the common scheme, and 80.5% under the proposed multi-class scheme, thus being suitable for detecting a SCD episode in advance.

Resampled dimensional reduction for feature representation in machine learning

We aimed to provide a resampling protocol for dimensional reduction resulting a few latent variables. The applicability focuses on but not limited for developing a machine learning prediction model in order to improve the number of sample size in relative to the number of candidate predictors. By this feature representation technique, one can improve generalization by preventing latent variables to overfit data used to conduct the dimensional reduction. However, this technique may warrant more computational capacity and time to conduct the procedure. The key stages consisted of derivation of latent variables from multiple resampling subsets, parameter estimation of latent variables in population, and selection of latent variables transformed by the estimated parameters.

LITERARY REALISM IN THE SHAPING OF SLOVAK CULTURE

Aim. The aim of the study is to clarify the internal complexity of the Slovak literary realist discourse and its diverse relations to the heterogeneous artistic, cultural and ideological discourses of the last third of the 19th century. Attention is focused on the appropriation and adaptation of stimuli from other social systems, as well as on the specific literary operations that modify literary realism as an artistic discourse constructing an intelligible world in a cultural sense. Methods. As a theoretical concept, realism is defined as a type of representation or representation technique associated with a set of textual conventions, complex referential and self-referential figures. As a literary-historical discourse and event situated in a particular moment of history, realism is governed by period-specific principles (operating in the mechanism of culture) of selection, evaluating and connecting the phenomena of reality. Only with this dichotomy the multiplicity of paradoxes, syncretism and heterogeneous character of Slovak literary realism can be captured. The theory of social systems (N. Luhmann) allows for a more complex view of realist literature as an autopoietic system in the context of modern society as a system of communications differentiated into a network of separate social subsystems interrelated by the medium of language. Finally, the theory of fictional worlds proposes selective and formative operations that explicate the construction of realist fictional world and the stratification of its functions (B. Fořt). Results. Among the configurational relations of Slovak literary realism, the concept of ideal realism is highlighted as a model of literary aesthetics that flexibly interacted with the discourse of national revival to provide an adequate expression of contemporary Slovak cultural and national interests. Two literary-aesthetic modifications of ideal realism (creative and voluntarist, originated by Svetozár Hurban Vajanský, and deterministic, represented in the prose works of Martin Kukučín) are analysed in detail in order to show the inner complexity of the literary-realist discourse and to manifest its semantic multidimensionality in the 1880s.

Teknik Penggambaran Aktor Terkait Perundungan Pasangan Gay Thailand di Koran Digital Indonesia

Actors Representation Technique Related to Thai Gay Couples Bullying in Indonesian Digital Newspapers ABSTRAKMedia sudah semakin mudah membuat dan menyebarkan berita karena kemajuan teknologi. Penelitian ini bertujuan untuk mengetahui ada atau tidaknya teknik yang digunakan oleh 5 koran digital Indonesia dalam mengeluarkan dan menggambarkan aktor atau peristiwa terkait pemberitaan perundungan pasangan gay Thailand oleh netizen Indonesia dan memaparkan teknik apa saja yang digunakan oleh 5 koran digital Indonesia itu. Metode yang digunakan adalah deskriptif kualitatif dan menggunakan teori analisis wacana kritis model Theo van Leeuwen. Penelitian ini menemukan teknik eksklusi berupa pasivasi 4 data dan nominasi 2 data, serta teknik inklusi berupa diferensiasi-indifernsiasi 1 data, objektivitas-abstraksi 4 data, nominasi-kategorisasi 2 data, nominasi-identifikasi 1 data, determinasi-indeterminasi 3 data, asimilasi-individualisasi 3 data dan asosiasi-disosiasi 1 data.Kata kunci: Analisis wacama kritis, Theo van Leeuwen, eksklusi, inklusiABSTRACTThe media has become easier to create and spread news because of technological advances. This research aims to determine whether or not there are techniques used by 5 Indonesian digital newspapers are available in issuing and describing actors or events related to the news of Thai gay couples bullying by Indonesian netizens and to explain what techniques are used by the 5 Indonesian digital newspapers. The method used is descriptive qualitative and uses critical discourse analysis theory by Theo van Leeuwen's model. This study found exclusion techniques in the form of 4 data passivation and 2 data nominations, as well as inclusion techniques in the form of 1 data differentiation-indifferentiation, 4 data objectivity-abstraction, 2 data nominations-categorization, 1 data nomination-identification, 3 data determination-indertermination, 3 data assimilation- individualization and 1 data association-dissociation.Keyword: critical discourse analysis, Theo van Leeuwen, exclusion, inclusion

Kontaktkutatás, vezetői információs rendszer

Összefoglaló. Tanulmányunkban bemutatjuk a hazai COVID-járvány első hulláma során kidolgozott informatikai megoldást, amely a kontaktkutatást hálózattudományi megközelítés alapján segítette, és hozzájárult az első hullám sikeres megfékezéséhez. A kifejlesztett vizuális reprezentációs technika látványos és részletekbe menő megértést, problémafeltárást képes biztosítani a járványügyi szakemberek számára. A grafikus elemek segítenek a gyors megértésben, a különböző hálózati elrendezések bizonyos jelenségekre, például gócpontokra, fertőzési klikkekre vagy a földrajzi terjedésre irányíthatják a figyelmet. A böngészőből történő futtatás alacsony technológiai belépési küszöböt biztosít a társterületeken kutatók számára, nekik így nem szükséges a problémafeltáráshoz külön szoftvereket telepíteni. Az adatbázis SQL-alapú szűrése a vizualizációs felületről lehetőséget biztosít összetettebb kérdések megfogalmazására is. Summary. In our study, we present an IT solution developed during the first wave of the domestic COVID epidemic. This tool served as an aid for contact tracing. The development focused on the network scientific aspects and contributed to the successful handling of the first wave. In case of absence of effective drugs or vaccines, controlling a contagious disease can only be achieved by preventing its spread. To this end infectious individuals must be identified, patients, exposed to the infection must be identified, the epidemic branching points that cause the greatest infection must be uncovered, information on the course of the disease must be collected, temporal and efficacy parameters must be determined, and potential cases of infection must be described. One possible way to accomplish these tasks is achieved by contact tracing. Classical contact tracing is carried out by personal data collection, during which the commissioned epidemiologist has to fill in a questionnaire. The questionnaire basically includes data used to identify the infected person, as well as the data of the persons who were in contact with the infected person, i.e. in contact with them. The effectiveness of the research is also enhanced if the questionnaire records disease-related parameters (e.g., symptoms, timing-related times, etc.) as well. Once the disease is known, questionnaires can be designed according to a definite template format, the organization of data collection groups and the associated costs can be planned in advance. However, in the case of a new, unknown disease, flexibility and the ability to adapt quickly during data collection are of paramount importance. The developed visual representation technique is able to provide spectacular and detailed understanding and a problem-solving user interface for epidemiologists. Graphical elements help in quick understanding, different network layouts can direct the attention to certain phenomena such as focal points, infectious cliques, or geographical spreading patterns. Running from a browser provides a low technology entry threshold for researchers in other scientific fields, so they don’t need to install separate software. The SQL-based filtering of the database on the visualization interface also provides an opportunity to study more complex questions. Thus, with the help of the presented computer system, a relational database can be generated from the initially unstructured data of the contact research protocols through several steps. The relational database is made available to analysts and decision-makers. As the final balance of the first wave of COVID-19 in Hungary showed, data from well-organized contact research and processed in appropriate analytical tools can provide important information for controlling the epidemic and saving lives.

Ascent Trajectory Optimization for Air-Breathing Hypersonic Vehicles Based on IGS-MPSP

This paper proposes an improved Generalized Quasi-Spectral Model Predictive Static Programming (GS-MPSP) algorithm for the ascent trajectory optimization for hypersonic vehicles in a complex flight environment. The proposed method guarantees the satisfaction of constraints related to the state and control vector while retaining its high computational efficiency. The spectral representation technique is used to describe the control variables, which reduces the number of decision variables and makes the control input smooth enough. Through Taylor expansion, the constraints are transformed into an inequality containing only decision variables, such that it can be added into GS-MPSP framework. By Gauss quadrature collocation method, only a few collocation points are needed to solve the sensitivity matrix, which greatly accelerates the calculation. Subsequently, the analytical expression is obtained by combining the static optimization with the penalty function method. Finally, the simulation results demonstrate that the proposed improved GS-MPSP algorithm can achieve both high computational efficiency and high terminal precision under the constraints.

Ontology-based Approach for Laptop Semantic Knowledge Representation

The rapid development of technology requires everyone to adapt. It is the same as the demands of work and school so that everyone should be more able to handle this problem. It is inevitable that the use of laptops today is not something that is a step. Almost all age groups use laptops to do school work, complete office work, or as a medium of entertainment. With so many types of laptops, some people are confused about choosing a laptop. The use of ontology as an information representation technique is a solution to this problem. Ontology can present information or knowledge sources semantically and organize various information resources in a systematic and structured manner. In the development of this ontology will be made using the methontology method. Methontology is one of the ontology model development methodologies which has advantages related to a detailed description of each activity. In addition, methontology also has other advantages, namely the development of ontology that are now made usable for further system development. Therefore, this study is proposed to build an ontology model that represents knowledge about laptops.

An efficient methodology for aspect-based sentiment analysis using BERT through refined aspect extraction

Aspect-Based Sentiment Analysis (ABSA) has become a trending research domain due to its ability to transform lives as well as the technical challenges involved in it. In this paper, a unique set of rules has been formulated to extract aspect-opinion phrases. It helps to reduce the average sentence length by 84% and the complexity of the text by 50%. A modified rank-based version of Term-Frequency - Inverse-Document-Frequency (TF-IDF) has been proposed to identify significant aspects. An innovative word representation technique has been applied for aspect categorization which identifies both local as well as global context of a word. For sentiment classification, pre-trained Bidirectional Encoder Representations from Transformers (BERT) has been applied as it helps to capture long-term dependencies and reduce the overhead of training the model from scratch. However, BERT has drawbacks like quadratic drop in efficiency with an increase in sequence length which is limited to 512 tokens. The proposed methodology mitigates these drawbacks of a typical BERT classifier accompanied by a rise in efficiency along with an improvement of 8% in its accuracy. Furthermore, it yields enhanced performance and efficiency compared to other state-of-the-art methods. The assertions have been established through extensive analysis upon movie reviews and Sentihood data-sets.

Deep Multi-Stage Approach For Emotional Body Gesture Recognition In Job Interview

Affective computing is a key research topic in artificial intelligence which is applied to psychology and machines. It consists of the estimation and measurement of human emotions. A person’s body language is one of the most significant sources of information during job interview, and it reflects a deep psychological state that is often missing from other data sources. In our work, we combine two tasks of pose estimation and emotion classification for emotional body gesture recognition to propose a deep multi-stage architecture that is able to deal with both tasks. Our deep pose decoding method detects and tracks the candidate’s skeleton in a video using a combination of depthwise convolutional network and detection-based method for 2D pose reconstruction. Moreover, we propose a representation technique based on the superposition of skeletons to generate for each video sequence a single image synthesizing the different poses of the subject. We call this image: ‘history pose image’, and it is used as input to the convolutional neural network model based on the Visual Geometry Group architecture. We demonstrate the effectiveness of our method in comparison with other methods in the state of the art on the standard Common Object in Context keypoint dataset and Face and Body gesture video database.