Elena Simona Apostol

Elena Simona Apostol
Polytechnic University of Bucharest | UPB

Doctor of Engineering

About

61
Publications
14,864
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
158
Citations

Publications

Publications (61)
Article
Full-text available
Water resource management represents a fundamental aspect of a modern society. Urban areas present multiple challenges requiring complex solutions, which include multidomain approaches related to the integration of advanced technologies. Water consumption monitoring applications play a significant role in increasing awareness, while machine learnin...
Conference Paper
Discovering the habits of consumers is essential for effective decision support in smart water networks. While smart water meters can provide detailed consumption data for individual households, additional information can be extracted based on the geographical coordinates to highlight the distribution of consumer behaviors within a given area. In t...
Article
Full-text available
This paper presents an overview of the LL(O)D and NLP methods, tools and data for detecting and representing semantic change, with its main application in humanities research. The paper’s aim is to provide the starting point for the construction of a workflow and set of multilingual diachronic ontologies within the humanities use case of the COST A...
Article
Full-text available
Developing artificial learning systems that can understand and generate natural language has been one of the long-standing goals of artificial intelligence. Recent decades have witnessed an impressive progress on both of these problems, giving rise to a new family of approaches. Especially, the advances in deep learning over the past couple of year...
Article
Full-text available
In the context in which it was demonstrated that humanoid robots are efficient in helping children diagnosed with autism in exploring their affective state, this paper underlines and proves the efficiency of a previously developed machine learning-based mobile application called PandaSays, which was improved and integrated with an Alpha 1 Pro robot...
Article
Full-text available
Misinformation is considered a threat to our democratic values and principles. The spread of such content on social media polarizes society and undermines public discourse by distorting public perceptions and generating social unrest while lacking the rigor of traditional journalism. Transformers and transfer learning proved to be state-of-the-art...
Conference Paper
Full-text available
Improving consumer profile evaluation is essential for effective water resource management, by creating a more accurate overview of the water distribution network. When compared to the classification by households, a data-driven approach can deliver more accurate results about the consumer types according to their behavior. Clustering methods are c...
Article
Full-text available
New mass media paradigms for information distribution have emerged with the digital age. With new digital-enabled mass media, the communication process is centered around the user, while multimedia content is the new identity of news. Thus, the media landscape has shifted from mass media to personalized social media. While this progress brings adva...
Article
Full-text available
Document-level Sentiment Analysis is a complex task that implies the analysis of large textual content that can incorporate multiple contradictory polarities at the phrase and word levels. Most of the current approaches either represent textual data using pre-trained word embeddings without considering the local context that can be extracted from t...
Preprint
Full-text available
Extracting top-k keywords and documents using weighting schemes are popular techniques employed in text mining and machine learning for different analysis and retrieval tasks. The weights are usually computed in the data preprocessing step, as they are costly to update and keep track of all the modifications performed on the dataset. Furthermore, c...
Conference Paper
Full-text available
Profiling consumers in a water distribution system is essential for achieving sustainability in terms of resource management and urban development. Unsupervised learning can provide data-driven decision support for evaluating the water demand patterns in a large network, while various pre-processing methods can be added to expand the level of detai...
Article
Full-text available
Due to the exponential growth of the Internet of Things networks and the massive amount of time series data collected from these networks, it is essential to apply efficient methods for Big Data analysis in order to extract meaningful information and statistics. Anomaly detection is an important part of time series analysis, improving the quality o...
Chapter
Full-text available
This paper introduces DenLAC (Density Levels Aggregation Clustering), an adaptable clustering algorithm which achieves high accuracy independent of the input’s shape and distribution. While most clustering algorithms are specialized on particular input types, DenLAC obtains correct results for spherical, elongated and different density clusters. We...
Article
Full-text available
Topic modeling is a probabilistic graphical model for discovering latent topics in text corpora by using multinomial distributions of topics over words. Topic labeling is used to assign meaningful labels for the discovered topics. In this paper, we present a new topic labeling method that uses automatic term recognition to discover and assign relev...
Conference Paper
Full-text available
Our society is undergoing a data explosion. To deal with these Big Data Sets both scientists and experts from industries are creating models, methods, techniques, algorithms for efficient analysis, sometimes in real-time and with different constraints. The main objective of this paper is to present several examples of datasets used in different res...
Preprint
Full-text available
In the current context of Big Data, a multitude of new NoSQL solutions for storing, managing, and extracting information and patterns from semi-structured data have been proposed and implemented. These solutions were developed to relieve the issue of rigid data structures present in relational databases, by introducing semi-structured and flexible...
Article
Full-text available
Extracting top-k keywords and documents using weighting schemes are popular techniques employed in text mining and machine learning for different analysis and retrieval tasks. The weights are usually computed in the data preprocessing step, as they are costly to update and keep track of all the modifications performed on the dataset. Furthermore, c...
Article
Full-text available
In the current context of Big Data, a multitude of new NoSQL solutions for storing, managing, and extracting information and patterns from semi-structured data have been proposed and implemented. These solutions were developed to relieve the issue of rigid data structures present in relational databases, by introducing semi-structured and flexible...
Conference Paper
Full-text available
Community detection is the process of extracting community structured subgraphs from community networks. Most research regarding community detection has focused on the network structure without taking the content associated with the nodes into account. In this paper, we propose a new method for enhancing a co-authorship network's structure using cl...
Conference Paper
Full-text available
Density-based clustering algorithms can accurately identify arbitrary shaped clusters, characteristic which makes them advantageous for many real-life datasets. However, most density-based clustering algorithms are affected by the curse of dimensionality, since they rely on distance metrics and range queries. In this paper, we demonstrate how densi...
Conference Paper
Full-text available
Sentiment analysis plays an important role in automatically finding the polarity and insights of users with regards to a specific subject, events, and entity. In this article, we propose a new topic-document embedding (TOPICDOC2VEC) for detecting the polarity of a text. The TOPICDOC2VEC is constructed as the concatenation between a document embeddi...
Chapter
Full-text available
A large number of real-world optimization and search problems are too computationally intensive to be solved due to their large state space. Therefore, a mechanism for generating approximate solutions must be adopted. Genetic Algorithms, a subclass of Evolutionary Algorithms, represent one of the widely used methods of finding and approximating use...
Chapter
Current networks should provide disaster-resilience by coping with the possible failures and misbehaviours caused by massive natural or man-made disasters. This is necessary to keep a suitable level of Quality of Service after a disaster and to support the possible evacuation, rescue, assessment, and rescue operations within the affected area. Mult...
Article
Full-text available
Water distribution is fundamental to modern society, and there are many associatedchallenges in the context of large metropolitan areas. A multi-domain approach is required fordesigning modern solutions for the existing infrastructure, including control and monitoring systems,data science and Machine Learning. Considering the large scale water dist...
Conference Paper
Full-text available
The TF-IDF model is the most common way of representing documents in the vector space. However, its results are highly dimensional, posing problems to the classic clustering algorithms due to the curse of dimensionality. Recent word embeddings based techniques can reduce the documents representations dimensionality while also preserving the semanti...
Conference Paper
Full-text available
Clustering is an important Data Mining operation that groups objects into clusters based on their similarity. The similarity join is a primitive operation used in clustering which retrieves the most similar pairs from two input data-sets based on a dissimilarity function (also named metric). In this article, we transform DBSCAN's (Density-Based Alg...
Preprint
Simulating the flow of different fluids can be a highly computational intensive process, which requires large amounts of resources. Recently there has been a lot of research effort directed towards GPU processing, which can greatly increase the performance of different applications, such as Smoothed Particle Hydrodynamics (SPH), which is most commo...
Article
Full-text available
As the number of interconnected devices grows in the IoT space, data processing systems require increased resources, robustness and exibility. In this sense the scalability of a system becomes very important. A scalable system can process variable data volumes, requires less costs for mainte- nance and allows for fault tolerance and high availabili...
Chapter
The goal of this chapter is to analyze existing solutions for self-aware Internet of Things. It will highlight, from a research perspective, the performance and limitations of existing architectures, services and applications specialized on healthcare. The chapter will offer to scientists from academia and designers from industry an overview of the...
Conference Paper
Full-text available
This paper proposes a new solution for topic modeling using contextual cues by applying Automatic Term Recognition (ATR) to extract domain-specific terms in the text preprocessing step. The vocabularies used for topic modeling are constructed using linguistic patterns to determine the inner structure of each document analyzed and, by only taking in...
Conference Paper
The MapReduce paradigm is one of the best solutions for implementing distributed applications which perform intensive data processing. In terms of performance regarding this type of applications, MapReduce can be improved by adding GPU capabilities. In this context, the GPU clusters for large scale computing can bring a considerable increase in the...
Conference Paper
Full-text available
Genetic Algorithms (GA) are a subclass of evolutionary algorithms that use the principle of evolution in order to search for solutions to optimization problems. Evolutionary algorithms are by their nature very good candidates for parallelization, and genetic algorithms do not make an exception. Moreover, researchers have stated that genetic algorit...
Article
Cloud-based systems expanded considerably in recent years, as the demand for cheaper and easily scalable resources provisioning solutions increased. In this context, the deployment of multimedia services in the cloud, as a way to increase their usability and overcome their processing overhead, gained additional interest. Throughout this paper we pr...
Article
Cloud computing describes the model of a scalable resource provisioning technology that redirects the possibility of hardware and software leasing to the Internet, through the use of an equitable pay-per-use strategy. In this paper we present a new provisioning mechanism in Clouds used for large-scale data-intensive computing. Our project addresses...
Conference Paper
The graphics processing units (GPUs) have become an integral part of today's computing systems. They have risen and evolved over the last years, becoming a platform for parallel computation with a large number of scalar processors and abundant memory bandwidth. They deliver high standard computation performance, but also require a lot of power supp...
Conference Paper
Multimedia services are advanced applications with large data sets, high computational resources prerequisites and distributed execution flows. The fairly new domain of cloud computing proposes a model of virtual resources management that fulfills the requirements of an efficient development and deployment environment for this type of services. Thr...
Conference Paper
This paper presents a flexible and reliable platform to access and manage services from a multiple-Cloud environment. The proposed platform facilitates user interaction with the resources provided by the Clouds for both service providers and service customers. It performs authentication, virtual resource and service level access management, and it...
Article
Nowadays, the wireless access network infrastructure is growing at an accelerated pace. In the current environment which consists of a multitude of wireless networks, live migration of multimedia streaming between different types of connectivity offers important advantages for mobile users. In this paper we provide the description of efficient mobi...
Article
Cloud Systems provide computing resources in a flexible manner. There are several key requirements that need to be addressed regarding the resource allocation in Clouds and the most important of them is providing on demand elasticity. This paper focuses on adding new features to the Cloud resource allocation mechanism that enhance on demand elastic...
Conference Paper
Nowadays, the wireless access network infrastructure is growing at an accelerated pace. In the current environment, which consists of a multitude of wireless networks, live migration of multimedia streaming between different type of connectivity offers important advantages for mobile users. In this paper we provide the description of an efficient m...
Article
Cloud Systems provide the computing infrastructure and on-demand capacity required to host services. In this paper we present a new provisioning mechanism for Cloud Systems. Our project addresses the key requirements in managing resources at the infrastructure level. The proposed resource manager allocates virtual resources in a flexible way, takin...
Article
Full-text available
We have extended the classical approach of a disk partition to a distributed environment. In this way, a NetFS partition is composed out of several storage fs nodes that are stored on different type of media and/or computer systems. The file system can be partially mounted, meaning that mounting can be done using only a subset of the fs nodes. Due...

Network

Cited By

Projects

Projects (2)
Project
The objective is to enhance the S&T abilities in the field of smart, data driven e-services in water management, with focus on the widening organization. The complexity of research related to water management is extremely high and requires deep expertise in several ICT-related research domains. The dynamics of water and the role of humans in the water cycle are not well understood largely because environmental and socioeconomic analyses are still performed separately. The specific objectives are: Enhance the science and technology capacity of the participating institutions; Raise staff’s research profile as well as the one of the institutions involved; Contribute to the Smart Specialization Strategy; Contribute to the development of a new, interdisciplinary research domain. Main activities in the project are: organization of workshops, summer schools; exchange and training of researchers; develop a road-map for the UPB, aligned with the partners’ research agendas in the area of IT for water management; development of a knowledge transfer and remote training system, and inclusion of UPB team in an operational research network. There search quality system will be set up, based on the Composite indicator of Research Excellence. The project will also help to raise staff’s research profile. The scientific strategy of the UPB team will be oriented towards inter/trans-disciplinary and practical applicability, valorization and impact in water management, which also fits to the Smart Specialization Strategy of Romania. The main expected impact is the increase of publications number with high visibility, and the creation of an active network with relevant stakeholders. The consortium was constituted so that it is representative for the research topic, that has a strong interdisciplinary character, with main focus on information technology. The project consortium consists of two leading research partners in the field of IT and a water management leading research partner.
Project
The overall objective of the proposal is to create an intelligent, integrated, cloud services-based system, using advanced computer technology, automation and communications to increase product quality and business development in the area of farming. The specific objective is to create an integrated control system for controlling the process in greenhouse crop production, using the services available on mobile devices. The services also offer simple and cheap integration of the existing infrastructure in various types of companies involved in agriculture. The added value generated by the system results from the creation of a virtual space that can be shared by several categories of companies.