- Service-Oriented Architecture and Web Services
- Advanced Software Engineering Methodologies
- Sentiment Analysis and Opinion Mining
- Topic Modeling
- Neural dynamics and brain function
- Context-Aware Activity Recognition Systems
- Semantic Web and Ontologies
- Advanced Text Analysis Techniques
- Neural Networks and Applications
- Text and Document Classification Technologies
- Web Data Mining and Analysis
- Time Series Analysis and Forecasting
- EEG and Brain-Computer Interfaces
- Mobile Agent-Based Network Management
- Natural Language Processing Techniques
- Complex Network Analysis Techniques
- Software System Performance and Reliability
- Multi-Agent Systems and Negotiation
- Business Process Modeling and Analysis
- Spam and Phishing Detection
- Music and Audio Processing
- Recommender Systems and Techniques
- Advanced Clustering Algorithms Research
- Neuroscience and Neural Engineering
- Data Management and Algorithms
Technical University of Cluj-Napoca
2015-2024
Laboratoire d'Informatique de Paris-Nord
2017-2024
Quark Pharmaceuticals (United States)
2009
National Institute for Research and Development of Isotopic and Molecular Technologies
2006
Spike sorting is the process of grouping spikes distinct neurons into their respective clusters. Most frequently, this performed by relying on similarity features extracted from spike shapes. In spite recent developments, current methods have yet to achieve satisfactory performance and many investigators favour manually, even though it an intensive undertaking that requires prolonged allotments time. To automate process, a diverse array machine learning techniques has been applied. The these...
The high popularity of modern web is partly due to the increase in number content sharing applications. social tools provided by applications allow online users interact, express their opinions and read from other users. However, spammers provide comments which are written intentionally mislead redirecting them sites rating promote products less known on market. Reading spam a bad experience waste time for most but can also be harming cause damage reader. Research has been performed this...
Eye-tracking is a method of recording the location gaze as well pupil diameter (dilation) during active visual behavior. Due to blinking and noise in system, these signals are often briefly "lost", leading missing data. Here, we aim analyze accuracy six interpolation methods complete values from Data type estimation that constructs new data existing, neighboring values. Having possibility choose different types methods, question which most suitable for applied linear method, previous...
Inspired from biology, in this paper we propose a hybrid firefly method for selecting the optimal solution semantic Web service composition. In our approach, search space of selection is represented by an Enhanced Planning Graph structure which encodes all composition solutions given user request. As criteria have considered QoS attributes services involved as well similarity between them. For evaluation proposed implemented experimental prototype and carried out experiments on scenario trip...
The Internet of Things is about data, different devices from places and the connectivity between them. Our goal to find a way interact with their according customer's requirements, in IoT context, all this supported by use Web services. We present broker based architecture for service selection which facilitates specify both functional non-functional requirements. develop device discovery recommendation mechanism on proposed web similarity metric.
The electroencephalography (EEG) data records vast amounts of human cerebral activity yet is still reviewed primarily by readers. Most the times, contaminated with non-cerebral originated signals, called artifacts, which could be very difficult to visually detect and, undiscovered, damage neural information analysis. purpose our work artifacts identifying most relevant features, both in temporal and frequency domains, train various supervised learning algorithms: Decision Trees, SVM KNN,...
This paper presents a technique for semantic Web service composition inspired by the behavior of ants. The proposed combines graph model with ant colony optimization met heuristic to select optimal solution. In our approach, we have considered as selection criteria QoS attributes services and quality connections between involved in
The main objective of this paper is the time-frequency analysis EEG signal captured in a cognitive task (i.e. object recognition) performed by human subjects. We investigate whether power spectral density gamma frequency range can be used to classify outcome recognition seen, unseen, uncertain). signals were acquired and analyzed from 128 electrodes located on all parts brain. Power features are extracted for classification support vector machine (SVM), K-Nearest Neighbor (KNN) Artificial...
As virtual home assistants are becoming more popular, there is an emerging need for supporting languages other than English. While wide-spread or popular such as Spanish, French Hindi already integrated into existing like Google Home Alexa, integration of less-known Romanian still missing. This paper explores the problem Natural Language Understanding (NLU) applied to a assistant. We propose customized capsule neural network architecture that performs intent detection and slot filling in...
In this paper we present a bee-inspired method for selecting the optimal composition solution. The proposed uses graph model and matrix of semantic links to search For improving performance traditional bee colony optimization algorithm 1-OPT heuristic is defined. This makes solutions more diverse so as avoid stagnation on local solutions. solution identified by using multi-criteria fitness function. function evaluates according QoS attributes quality between services involved in
This paper presents a Tabu search-based method for selecting the optimal or near-optimal solution in semantic Web service composition. The proposed is applied on an Enhanced Planning Graph structure which encodes all composition solutions that satisfy user request. criteria include QoS attributes and similarity between services involved was evaluated scenarios from trip planning domain.
Sentiment classification is not a new topic but data sources having different characteristics require customized methods to exploit the hidden existing semantic while minimizing noise and irrelevant information. Twitter represents huge pool of specific features. We propose therefore an unsupervised, domain-independent approach, for sentiment on Twitter. The proposed approach integrates NLP techniques, Word Sense Disambiguation unsupervised rule-based classification. method able differentiate...
In the context of current technological progress, big data arises as a compelling research topic. This paper presents non-traditional analysis strategies like exploiting semantics (cycle identification) well traditional ones (signal interpolation and correlation) for industrial within Big Data paradigm. A general approach preprocessing operations exploring extracting valuable knowledge from large set is defined. The identified are tested validated on real characterized by multitude...
This paper addresses the problem of traceability in context a complex supply chain by proposing model that captures main elements necessary to follow product throughout its lifecycle, from manufacturing end consumer. The is general enough be applied for several types chains and focuses on external traceability, but also enables retrieval internal data. We present broker-based service oriented architecture provides logistics support according model. operations are performed products travel...
This paper addresses two fundamental research problems in the domain of context sensitive systems: development a generic model that can be used to represent general purpose contexts computer interpretable way and management. The is represented using triple set consisting resources, actors policies. mapped onto real by populating sets with specific elements. A situation which aware system must adapt instance. To ease reasoning adaptation processes, core ontology defined relationships between...
This paper presents a system for identifying communities in networks built based on opinions and social data. We show how we can build graphs from interactions identify the community structure of these graphs. handle both types data: one-dimensional multidimensional. As detection method, use Infomap algorithm. The dimensions considered are one or many attributes. contradictions be detected using identified communities.
SUMMARY The clustering and sorting behavior of ants, as well the foraging birds in nature represented sources inspiration for designing methods applicable computer science. This paper investigates how biologically‐inspired can be adapted to cluster Semantic Web services aiming at efficiency discovery process. consider semantic similarity between main criterion. To measure two services, we propose a matching method that evaluates degree match description services. We have tested on SAWSDL...
This paper analyses the impact of biological intelligence on problem selecting optimal solution in Web service composition. Thus, we propose two selection methods, one inspired by behaviour bees searching for food and another cuckoos nests where to lay eggs. The methods use a composition graph search solution. quality is evaluated based QoS semantic quality. To comparatively analyse proposed implemented an experimental prototype performed tests set scenarios from trip planning.
E-learning is nowadays one of the most interesting "e- " domains available through Internet. The main problem to create a Web-based, virtual environment model traditional domain and implement using suitable technologies. We analyzed distance learning investigated possibility some e-learning services mobile agent This paper presents Student Assessment Service (SAS) an agent-based framework developed be used for implementing specific applications. A application that relies on was developed.
This paper proposes a generic policy based self-management model that can be used to automatically detect and repair the problems appeared during context adaptation processes. To successfully capture evaluate dynamic rules govern aware processes we have defined an representation its associated reasoning language conversion for run-time evaluation. degree of respecting policies define formalize concept entropy. The information is modeled in system programmatic manner using both set ontology...