Dual Gated Graph Attention Networks with Dynamic Iterative Training for Cross-Lingual Entity Alignment

Cross-lingual entity alignment has attracted considerable attention in recent years. Past studies using conventional approaches to match entities share the common problem of missing important structural information beyond entities in the modeling process. This allows graph neural network models to step in. Most existing graph neural network approaches model individual knowledge graphs (KGs) separately with a small amount of pre-aligned entities served as anchors to connect different KG embedding spaces. However, this characteristic can cause several major problems, including performance restraint due to the insufficiency of available seed alignments and ignorance of pre-aligned links that are useful in contextual information in-between nodes. In this article, we propose DuGa-DIT, a dual gated graph attention network with dynamic iterative training, to address these problems in a unified model. The DuGa-DIT model captures neighborhood and cross-KG alignment features by using intra-KG attention and cross-KG attention layers. With the dynamic iterative process, we can dynamically update the cross-KG attention score matrices, which enables our model to capture more cross-KG information. We conduct extensive experiments on two benchmark datasets and a case study in cross-lingual personalized search. Our experimental results demonstrate that DuGa-DIT outperforms state-of-the-art methods.

Prediction of Water Level Using Time Series, Wavelet and Neural Network Approaches

To control water resources in many domains such as agriculture, flood forecasting, and hydro-electrical dams, forecasting water level needs to predict. In this article, a new computational approach using a data driven model and time series is proposed to calculate the forecast water level in short time. Concretely, wavelet-artificial neural network (WAANN) and time series (TS) are combined together called WAANN-TS that encourages the advantage of each model. For this real time project work, Yen Bai station, Northwest Vietnam was chosen as an experimental case study to apply the proposed model. Input variables into the Wavelet-ANN structure is water level data. Time series and ANN models are built, and their performances are compared. The results indicate the greater accuracy of the proposed models at Hanoi station. The final proposal WAANN−TS for water level forecasting shows good performance with root mean square error (RMSE) from 10−10 to 10−11.

Applications of Big Data and AI in Electric Power Systems Engineering

The production, transmission, and distribution of energy can only be made stable and continuous by detailed analysis of the data. The energy demand needs to be met by a number of optimization algorithms during the distribution of the generated energy. The pricing of the energy supplied to the users and the change for investments according to the demand hours led to the formation of energy exchanges. This use costs varies for active or reactive powers. All of these supply-demand and pricing plans can only be achieved by collecting and analyzing data at each stage. In the study, an electrical power line with real parameters was modeled and fault scenarios were created, and faults were determined by artificial intelligence methods. In this study, both the power flow of electrical power systems and the methods of meeting the demands were investigated with big data, machine learning, and artificial neural network approaches.

Monitoring Population Phenology of Asian Citrus Psyllid Using Deep Learning

Asian citrus psyllid, Diaphorina citri Kuwayama (Liviidae: Hemiptera) is a menacing and notorious pest of citrus plants. It vectors a phloem vessel-dwelling bacterium Candidatus Liberibacter asiaticus, which is a causative pathogen of the serious citrus disease known as Huanglongbing. Huanglongbing disease is a major bottleneck in the export of citrus fruits from Pakistan. It is being responsible for huge citrus economic losses globally. In the current study, several prediction models were developed based on regression algorithms of machine learning to monitor different phenological stages of Asian citrus psyllid to predict its population about different abiotic variables (average maximum temperature, average minimum temperature, average weekly temperature, average weekly relative humidity, and average weekly rainfall) and biotic variable (host plant phenological patterns) in citrus-growing regions of Pakistan. The pest prediction models can be used for proper applications of pesticides only when needed for reducing the environmental and cost impacts of pesticides. Pearson’s correlation analysis was performed to find the relationship between different predictor (abiotic and biotic) variables and pest infestation rate on citrus plants. Multiple linear regression, random forest regressor, and deep neural network approaches were compared to predict population dynamics of Asian citrus psyllid. In comparison with other regression techniques, a deep neural network-based prediction model resulted in the least root mean squared error values while predicting egg, nymph, and adult populations.

Collocation polynomial neural forms and domain fragmentation for solving initial value problems

Several neural network approaches for solving differential equations employ trial solutions with a feedforward neural network. There are different means to incorporate the trial solution in the construction, for instance, one may include them directly in the cost function. Used within the corresponding neural network, the trial solutions define the so-called neural form. Such neural forms represent general, flexible tools by which one may solve various differential equations. In this article, we consider time-dependent initial value problems, which require to set up the neural form framework adequately. The neural forms presented up to now in the literature for such a setting can be considered as first-order polynomials. In this work, we propose to extend the polynomial order of the neural forms. The novel collocation-type construction includes several feedforward neural networks, one for each order. Additionally, we propose the fragmentation of the computational domain into subdomains. The neural forms are solved on each subdomain, whereas the interfacing grid points overlap in order to provide initial values over the whole fragmentation. We illustrate in experiments that the combination of collocation neural forms of higher order and the domain fragmentation allows to solve initial value problems over large domains with high accuracy and reliability.

More than the sum of its parts: Merging network psychometrics and network neuroscience with application in autism

Network approaches that investigate the interaction between symptoms or behaviours have opened new ways of understanding psychological phenomena in health and disorder. In parallel, network approaches that characterise the interaction between brain regions have become the dominant approach in neuroimaging research. Combining these parallel approaches would enable new insights into the interaction between behaviours and their brain-level correlates. In this paper, we introduce a methodology for combining network psychometrics and network neuroscience. This approach utilises the information from the psychometric network to obtain neural correlates for each node in the psychometric network (network-based regression). We illustrate the approach by highlighting the interaction between autistic traits and their resting-state functional associations. To this end, we utilise data from 172 male autistic participants (10–21 years) from the autism brain data exchange (ABIDE, ABIDE-II). Our results indicate that the network-based regression approach can uncover both unique and shared neural correlates of behavioural measures. In addition, the methodology enables us to isolate mechanisms at the brain-level that are unique to particular behavioural variables. For instance, our example analysis indicates that the overlap between communication and social difficulties is not reflected in the overlap between their functional correlates.

Integrating Role of the Conception of Language Personality in the Development of the Theory of Language

The article discusses the psycholinguistic explication of the phenomenon of the Russian language personality (RLP) on the experimentally obtained associative-verbal-network (AVN) model at the end of the XXth century and the methodological contribution of the RLP conception, proposed by Yu.N. Karaulov, to the development of a general theory of language. As a human-species-specific universal, LP can be studied within an interdisciplinary approach which suggests a complementary synthesis of the latest methodological and factological achievements in different branches of human sciences. All the facets of language functioning (systemic-structural, historical-cultural, psychological, and socio-communicative), that were highlighted earlier by Yu.N. Karaulov, are subject of interdisciplinary consideration, integrated within the conception of LP. Thus, conditions are created for a complementary use of the structural theory of language (whereby the language is viewed as an external object ) and a current theory of language within a person . Network approaches, widely used in a number of human sciences, help to identify different aspects of human formation. Yu.N. Karaulov proved that LP can be explicated only as a culturally-specific variety on the AVN model. This allows the author of the article to refer to the notion of intentional personality , that has been proposed by ethnologists and cultural anthropologists for their studies of the motivational aspects in socio-communicative interactions within a single cultural community. The author finds it appropriate to extrapolate the concept intentionality to the LP as a sense-generating and sense-organizing entity setting more-or-less flexible systematic stability to the persons internal image of the world and projecting this, often illogically organized, systematicity to the AVN. The advantages of using AVN model, in contrast to other network approaches, consist in its being capable to reflect the dominant socio-communicative attitudes which developed spontaneously by a natural order of emergence as the result of socialization of the studied community members. The author proceeds from an assumption about semantic accentuations of the LP as the units of analysis which are represented by fluctuations of associative dominants at the macrostructure and microlevels of the AVN; the empirical findings collected in the AVN may be regarded as initial data encouraging investigators to build hypotheses about the psychodynamic processes reflecting variability in socio-communicative environment. The range of fluctuations of the associative dominants at the turn of the century is shown as the statistic dimensions of the RLP in the network from the newest Russian regional associative database СИБАС1 [2008-2013] and СИБАС2 [2014-2020] in comparison with the Russian associative thesaurus (RAS) previously obtained by Russian psycholinguists, with Yu.N. Karaulovs active participation, in the years of perestroika [1988-1997].