semantic parsing of telecommunications data from nodes is an important topic of research in network monitoring and diagnostics. This data contains insights to achieve higher data rates, low latency and reliability. Th...
详细信息
ISBN:
(纸本)9781665423830
semantic parsing of telecommunications data from nodes is an important topic of research in network monitoring and diagnostics. This data contains insights to achieve higher data rates, low latency and reliability. The current machine learning algorithm relies heavily on iterative meta-heuristics tools for data mining. Such tools often fail to capture the consistency, and complementary information inadequately which results in loss of high-level semantic information that can be used to extract features inside unstructured text data. The features learned by the current Machine learning algorithm can perform classification of unstructured data with high accuracy. However, the same methods fail to extract entities from data with high variation in structure and uneven density of words. Manual steps to parse and extract relevant information have failed to provide higher efficiency in extracting useful information which delays the process of network analysis. In this paper, we present an Adaptive Deep Reinforcement (ADR) framework fused with a Deep Q Network (DQN) for feature extraction and LSTM to extract relational dependency of words in unstructured data. A novel dynamic optimizer component based on LSTM and fully connected layers is adopted for dynamic state reformulation and Q values greatly enhance the parsing accuracy by extracting robust features to measure variation in data and identifying relationships between entities in raw data to parse them to a structured format. We compare ADR with state-of-the-art Drain parser. The complexity comparison of parsed files with state-of-the-art and ADR demonstrates the effectiveness of the proposed framework for semantic parsing of unstructured data.
The challenge of managing and extracting useful knowledge from social media data sources has attracted much attention from academics and industry. To address this challenge, semantic analysis of textual data is focuse...
详细信息
The challenge of managing and extracting useful knowledge from social media data sources has attracted much attention from academics and industry. To address this challenge, semantic analysis of textual data is focused on in this paper. We propose an ontology-based approach to extract semantics of textual data and define the domain of data. In other words, we semantically analyze the social data at two levels: the entity level and the domain level. We have chosen Twitter as a social channel for the purpose of concept proof. Ontologies are used to capture domain knowledge and to enrich the semantics of tweets, by providing specific conceptual representation of entities that appear in the tweets. Case studies are used to demonstrate this approach. We experiment and evaluate our proposed approach with a public dataset collected from Twitter and from the politics domain. The ontology-based approach leverages entity extraction and concept mappings in terms of quantity and accuracy of concept identification.
Image geolocalization has become an important research field during the last decade. This field is divided into two main sections. The first is image geolocalization that is used to find out which country, region or c...
详细信息
Image geolocalization has become an important research field during the last decade. This field is divided into two main sections. The first is image geolocalization that is used to find out which country, region or city the image belongs to. The second one is refining image localization for uses that require more accuracy such as augmented reality and three dimensional environment reconstruction using images. In this paper we present a processing chain that gathers geographic data from several sources in order to deliver a better geolocalization than the GPS one of an image and precise camera pose parameters. In order to do so, we use multiple types of data. Among this information some are visible in the image and are extracted using image processing, other types of data can be extracted from image file headers or online image sharing platforms related information. Extracted information elements will not be expressive enough if they remain disconnected. We show that grouping these information elements helps finding the best geolocalization of the image.
The richest region in biodiversity in the world, the Amazon, became object of extreme attention and target for multidisciplinary scientific studies. Collected data from forests and rivers' expeditions generate a l...
详细信息
ISBN:
(纸本)9789806560536
The richest region in biodiversity in the world, the Amazon, became object of extreme attention and target for multidisciplinary scientific studies. Collected data from forests and rivers' expeditions generate a large volume of data that are managed supported by databases technology that are useful for strategic planning of the future of the region and its contribution to the planet. The data treated and manipulated by each experiment constitute, strategic information for others scientific studies. The data used by scientific experiments in the Amazon are described in a semi-structured form, which make conventional approaches of data modelling inappropriate for the process of database design. The infrastructure and technologies to support semi-structured data must offer solutions for the problems created by the data heterogeneity. Computer technology is a fundamental resource applied for biodiversity information management. In the scope of our study, the need of using ontology for extracting semi-structured data of scientific documents appears, taking into account the semantic aspects of these data and its need of interoperability. This paper presents an approach for semantic data extraction using ontology, the integration aspects of the suitable ontology applied to Amazonian biodiversity data documents.
暂无评论