A Hybrid Model for Power Consumption Forecasting Using VMD-Based the Long Short-Term Memory Neural Network

Energy consumption prediction is a popular research field in computational intelligence. However, it is difficult for general machine learning models to handle complex time series data such as building energy consumption data, and the results are often unsatisfactory. To address this difficulty, a hybrid prediction model based on modal decomposition was proposed in this paper. For data preprocessing, the variational mode decomposition (VMD) technique was used to used to decompose the original sequence into more robust subsequences. In the feature selection, the maximum relevance minimum redundancy (mRMR) algorithm was chosen to analyse the correlation between each component and the individual features while eliminating the redundancy between individual features. In the forecasting module, the long short-term memory (LSTM) neural network model was used to predict power consumption. In order to verify the performance of the proposed model, three categories of contrast methods were applied: 1) Comparing the hybrid model to a single predictive model, 2) Comparing the hybrid model with the backpropagation neural network (BPNN) to the hybrid model with the LSTM and 3) Comparing the hybrid model using mRMR and the hybrid model using mutual information maximization (MIM). The experimental results on the measured data of an office building in Qingdao show that the proposed hybrid model can improve the prediction accuracy and has better robustness compared to VMD-MIM-LSTM. In the three control groups mentioned above, the R2 value of the hybrid model improved by 10, 3 and 3%, respectively, the values of the mean absolute error (MAE) decreased by 48.9, 41.4 and 35.6%, respectively, and the root mean square error (RMSE) decreased by 54.7, 35.5 and 34.1%, respectively.

GENESIS OF THE «WOMAN’S» WAR IN CREATIVITY OF SVETLANA ALEXIEVICH (BASED ON THE MATERIAL OF THE NOVELS «THE UNWOMANLY FACE OF WAR» AND «ZINKY BOYS»)

The article examines the features of a fiction-documentary comprehension of the German-Soviet and Soviet-Afghan wars in the novels of Svetlana Alexievich «The unwomanly face of war» and «Zinky Boys». It occurs through the perception of a woman as a direct participant in the war, a mother, wife, whose war took away the most expensive – son, husband, father. The presence of archetypal images to combine separate chapters is common in both novels. In both her novels, S. Alexievich gave the archetypal image of a woman-keeper of modern sound, individual features, convincing the reader that this image is always relevant because each talented artist revealed not only its original meaning, but also created something new that was close to the man of each century.

Features and perspectives of international cooperation within the implementation of projects megascience class

The article presents aspects of the legal regulation of international scientific cooperation aimed at the creation and operation of unique scientific installations of the “megascience” class. On the example of scientific projects CERN, ITER and XFEL, the individual features of legal regulation are analyzed: the legal basis, the key provisions of the concluded international agreements, as well as the relationship with the Russian legislation. On the basis of the analysis and generalization, the authors identify the features of legal regulation, which should be taken into account when creating future scientific projects of the “megascience” class.

The Child in the Process of Education – Connotations of Styles of Knowledge Acquisition

Human brain is set of connections, circuits and countless branches and blockers. Individual features decide on way of information absorption. It is possible to observed a kind of programming of the method of receiving and selecting information.

Iconography as a Trigger? On Barbarious Imitations of Seleukids Coins

В работе рассматриваются ключевые проблемы иконографии варварских подражаний монетам Селевкидов на примере двух монетных серий — согдийских подражаний монетам Антиоха Iи коммагенских подражаний монетам Деметрия I. Обе монетные серии демонстрируют как общие тенденции семиотической трансформации нарратива монеты, происходящей при преобразовании оригинального монетного изображения в подражание, так и индивидуальные особенности этого процесса. Так, основным признаком трансформации нарратива монеты является изменения легенды. В случае с согдийскими подражаниями текст легенды, не воспринимавшейся аудиторий подражания как источник информации и коммуникации, преобразуется в орнамент и формирует часть изображения, а в случае с коммагенскими подражаниями, где текст легенды, очевидно, имел важную смысловую нагрузку, дополняется новыми, не характерными для оригинала эпитетами. Важным аспектом проблемы варварских подражаний является выбор иконографического сюжета. Этот выбор не был случаен и определялся культурной близостью сюжета, представленного на монете-прототипе. Таким образом, процесс создания подражания не сводился только к механическому копированию изображения, но представлял собой более содержательный процесс переосмысления текста изображения и перевод его на язык иной знаково-иконической системы посредствам особых художественных приемов. The paper surveys the key problems of iconography of barbarous imitations of Seleukid coins on the example of two-coin series — Sogdian imitations of coins of Antiochus I and Commagene imitations of Demetrius I. These coin series demonstrate both the general trends of the semiotic transformation of the narrative of the coin, which occurs in in the process of the transformation of original coin image into an imitation, and the individual features of this process. Thus, the main feature of the transformation of the coin narrative is the deviation of the legend. In the case of Sogdian imitations, the text of the legend, which was not considered by the audience of imitation as a source of information, is transformed into an ornament and constructs a part of the image, while in the case of Commagene imitations, where the text obviously was semantically determined, it is supplemented with new epithets that are not typical for the original. An important aspect of the problem of barbarous imitations is the choice of an iconographic motif. This choice was not accidental and was influenced by the cultural familiarity with the object depicted on the prototype coin. Thus, the process of creating an imitation was not only mechanical copying of the image, but represented a more meaningful process of rethinking the image text and translating it into the language of another iconic system through special artistic techniques.

Effects of Breath-Holding Tests on PetCO2 and Arterial Blood Oxygenation in Men

To evaluate the state of external respiration system, breath-holding tests are usually used. However, there are few studies of the peculiarities of the gas exchange in breath-holding with previous hyperventilation. The purpose of the study was to analyze the dynamics of changes in the PetCO2 level and arterial blood oxygenation during breath-holding tests with and without previous hyperventilation in healthy young men. Materials and methods. The СО2 level was recorded in the side stream on the Datex Normocap capnograph (Datex, Finland). This value was recorded for 5 minutes at rest, 5 minutes after half-breath hold, for 5 minutes of regulated breathing with a frequency of 30 cycles per minute, 5 minutes after half-breath hold. The capnogram, atmospheric pressure level and humidity were used to assess the level of СО2 at the end of exhalation (PetCO2), respiratory rate, the ratio of inspiratory duration to expiratory duration (Rie). Statistical processing of the results was performed by parametric methods. According to the method of sigmoid deviation, three groups of individuals were distinguished by the PetCO2 level: I – PetCO2 < 32.7 mmHg, II – PetCO2 – 32.7-36.2 mmHg, III – PetCO2 > 36.2 mmHg. Results and discussion. Breath-holding during the test after hyperventilation was significantly greater than in the first attempt (62.99±3.31 s and 33.78±2.24 s, p <0.001). Visual qualitative and quantitative analysis of capnograms and graphs of arterial blood oxygenation revealed significant inter-individual features of the reactions of these indicators to tests. Therefore, changes in PetCO2 were compared depending on its initial level. After the breath-holding test, the PetCO2 levels on average during the 5-minute recovery reliably decreased in groups II and III compared with I. During the test with hyperventilation, a natural significant increase in its level of reactivity was registered, most pronounced in group III (-13.48 mmHg, p <0.001). After the second breath-holding, there was a decrease in PetCO2 compared to the level after the first breath-holding in all groups. However, the level of HbO2 in the tests differed only in group II. Thus, after a breath-holding test, individuals with relatively low PetCO2 did not have its decrease in contrast to those with relatively medium and high levels. The use of hyperventilation potentiates these reactions before breath-holding, and aligns their level after a long recovery period in different groups. Conclusion. The study shows that breath-holding tests without and after hyperventilation significantly affect the level of CO2 stress and arterial blood oxygenation; the breath-holding test after hyperventilation potentiates the decrease in PetCO2 and HbO2 in arterial blood by increasing breath-holding time. There are significant individual features in the reactivity of such physiological parameters

EXPRESS: Remembered Together: Social interaction facilitates retrieval while reducing individuation of features within bound representations.

When encountering social scenes, there appears to be rapid and automatic detection of social interactions. Representations of interacting people appear to be bound together via a mechanism of joint attention, which results in enhanced memory, even when participants are unaware that memory is required. However, even though access is facilitated for socially bound representations, we predicted that the individual features of these representations are less efficiently encoded, and features can therefore migrate between the constituent interacting individuals. This was confirmed in Experiment 1, where overall memory for interacting compared to non-interacting dyads was facilitated but binding of features within an individual was weak, resulting in feature migration errors. Experiment 2 demonstrated the role of conscious strategic processing, where participants were aware that memory would be tested. With such awareness, attention can be focused on individual objects allowing the binding of features. The results support an account of two forms of processing: An initial automatic social binding process where interacting individuals are represented as one episode in memory facilitating access; and a further stage where attention can be focused on each individual enabling the binding of features within individual objects.

Validation on Real Data of an Extended Embryo-Uterine Probabilistic Graphical Model for Embryo Selection

Embryo selection is a critical step in assisted reproduction (ART): a good selection criteria is expected to increase the probability of inducing pregnancy. In the past, machine learning methods have been used to predict implantation and to rank the most promising embryos. Here, we study the use of a probabilistic graphical model that assumes independence between embryos’ individual features and cycles characteristics. It also accounts for a third source of uncertainty attributed to unknown factors. We present an empirical validation and analysis of the behavior of the model within real data. The dataset describes 604 consecutive ART cycles carried out at Hospital Donostia (Spain), where embryo selection was performed following the Spanish Association for Reproduction Biology Studies (ASEBIR) protocol, based on morphological features. The performance of our model is evaluated with different metrics and the predicted probability densities are examined to obtain significant insights about the process. Special attention is given to the relation between the model and the ASEBIR protocol. We validate our model by showing that its predictions show correlation with the ASEBIR score when the score is not provided as a feature. However, once the selection based on this protocol has taken place, our model is unable to separate implanted and failed embryos when only embryo individual features are used. From here, we can conclude that ASEBIR score provides a good summary of morphological features.

Selfhood and Subjectivity in Sufi Thought: Image of a Mole on Emperor Akbar’s Nose

This paper addresses the making of portrait-images of Mughal emperors, in which distinctness and particularity in individual features distinguished portraits of emperor Akbar from his ancestors and successors. Scholars have argued that the technique of ‘accurate’ portraits or mimesis was introduced to Mughal artists with the arrival of renaissance paintings and prints from Europe, brought by Jesuit priests to the Mughal court. However, the question of why Mughal emperors saw a need to arrive at portraiture in the likeness of individuals remains to be addressed. This paper argues that the desire to portray a ruler, in all his individual particularity, can arise only within a literary and intellectual matrix in which the individual is valued and where ideas about selfhood and subjectivity have already permeated the philosophical, political, and literary thought. Tracing the transhistorical and transcultural migration of ideas and motifs from Timurid Central Asia to Mughal India, this paper examines the transference of Sufi thought on image-making practices, particularly portraiture, in the imperial court of the Mughals in early seventeenth century. Keywords: Portrait-images of Akbar, subjectivity, Sufi thought, poetics between text and image.