Browsing by Author "Dobre, Ciprian"
Now showing 1 - 20 of 33
Results Per Page
- ItemA New Challenge in the Data Processing of Non-Standard Texts Containing Accents / Diacritics: A Case Study(IEEE, 2019) Gavrilă, Veronica; Băjenaru, Lidia; Dobre, CiprianThe INTELLIT project develops a virtual online museum of the Romanian literature. The sources of data made available and provided by the Romanian Academy, such as: General Dictionary of Romanian Literature, Timeline of the Romanian Literary Life and the canonical works of Romanian writers are digitized and indexed using smart text analytics. One of the challenges with this process is dealing with diacritics and textual accents. Here, we present an in-depth analysis of possible solutions and describe our implementation for detecting various Unicode text processing. We present the solution identified as an accessible way to remove specific Unicode text code points in order to greatly improve our search and filtering capabilities while still preserving the original source (at the database level).
- ItemA New Challenge in the Data Processing of Non-Standard Texts Containing Accents / Diacritics: A Case Study(2019) Gavrilă, Veronica; Băjenaru, Lidia; Dobre, CiprianThe INTELLIT project develops a virtual online museum of the Romanian literature. The sources of data made available and provided by the Romanian Academy, such as: General Dictionary of Romanian Literature, Timeline of the Romanian Literary Life and the canonical works of Romanian writers are digitized and indexed using smart text analytics. One of the challenges with this process is dealing with diacritics and textual accents. Here, we present an in-depth analysis of possible solutions and describe our implementation for detecting various Unicode text processing. We present the solution identified as an accessible way to remove specific Unicode text code points in order to greatly improve our search and filtering capabilities while still preserving the original source (at the database level).
- ItemA New Digital Solution for Promoting of Romanian Literary Patrimony(Romanian Academy-Centre for Transylvanian Studies, 2019-03-31) Băjenaru, Lidia; Gavrilă, Veronica; Cristescu, Irina; Iordache, Dragoş Daniel; Dobre, CiprianA way of highlighting and promoting the most important and significant components of the national heritage is to harness them through Internet-based technologies. This paper presents the proposed digital solution for the promotion and preservation of collections of information from the Romanian literary patrimony using intelligent digital solutions for the extraction and systematization of knowledge. This digital solution, a platform, will offer advanced, intelligent semantic search and analysis services and prediction forms concerning Romanian literature. This paper presents several important platforms, systems and projects that are linked to the Literary Heritage. Then, a comparative analysis of the functionality, limitations and opportunities of the most relevant online platforms is presented, followed by the description of the main features of INTELLIT platform.
- ItemAcceptability of Digital Quality of Life Questionnaire Corroborated with Data from Tracking Devices(IEEE, 2019) Drăghici, Rozeta; Rusu, Alexandra; Prada, Gabriel Ioan; Herghelegiu, Anna Marie; Băjenaru, Lidia; Dobre, CiprianThe vINCI technology has a modular construction therefore the acceptability of each device will be assessed and further technological adaptation and modification will be performed based on older peoples feedback in a step by step manner. To avoid biased feedback and outcome due to previous usage of vINCI devices, different samples of seniors will be selected for each stage of the vINCI testing and validation. The vINCI modular technology comprises of different devices such as intelligent tablet (IT), smart watch (SW), smart insole (SI) and smart camera (SC). At this stage of the study we are testing the acceptability of a digital Quality of Life Questionnaire and we want to determine what information offers each type of tracking devices. The results of the study will allow us to determine at what stage of evolution of subjects over the age of 65 it will be necessary to introduce each of the four devices in order to obtain enough data or information to make decisions that prevent the aggravation of some diseases, or various accidents at home or during persons walking.
- ItemActivity Recognition for Ambient Assisted Living Using Off-the-shelf Motion Sensing Input Devices(IEEE, 2019) Cebanov, Elena; Dobre, Ciprian; Grădinaru, Alexandru; Ciobanu, Radu-Ioan; Stanciu, Valeriu-DanielIn recent years, healthcare and safety monitoring for older adults has become a worldwide concern. As older adults want to age at home, sensor technology has the potential to support their choice by monitoring health status, detecting emergency situations and notifying caregivers in case of emergency situations. Moreover, using new technologies such as the Kinect sensor could bring new ways to build in-home intelligent systems, having already demonstrated performance and accuracy when monitoring older adults. The purpose of this paper is to present an application that allows healthcare providers to take care remotely of older adults by providing live monitoring of the patients. Using a Kinect sensor, the application evaluates the active life of the tracked person, determines the hydration status and notifies the caregiver if the patient is calling for help or needs an ambulance.
- ItemAdvanced Methods to Extract Value from Scientific Datasets(Springer, 2019) Perju, Lucian; Nicolaescu, Marius-Dorian; Pop, Forin; Dobre, Ciprian; Maiduc, SandaIn these days the scientific community is times bigger comparing with the previous centuries. The need of powerful tools to aggregate and analyse the information about articles, books and other publications becomes greater with each published paper. In this paper we describe a solution for understanding and leveraging this data. The platform integrates the following requirements: data aggregation, data analysis (visualizations, dashboards, graphs), complex and simple searches, and support for data export. The platform brings value to its users due to various reasons such as quick identification of relevant data and in depth analysis on the provided input. Another key feature is the granularity, application being easily configurable for rigorous use cases: just one author, a group of authors or an entire scientific field.
- ItemAvoiding Data Corruption in Drop Computing Mobile Networks(Elsevier, 2019) Ciobanu, Radu-Ioan; Tăbușcă, Vlăduţ Constantin; Dobre, Ciprian; Băjenaru, Lidia; Mavromoustakis, Constandinos; Mastorakis, GeorgeDrop computing is a network paradigm that aims to address the issues of the mobile cloud computing model, which has started to show limitations especially since the advent of the Internet of Things and the increase in the number of connected devices. In drop computing, nodes are able to offload data and computations to the cloud, to edge devices, or to the social-based opportunistic network composed of other nodes located nearby. In this paper, we focus on the lowest layer of drop computing, where mobile nodes offload tasks and data to and from each other through close-range protocols, based on their social connections. In such a scenario, where the data can circulate in the mobile network on multiple paths (and through multiple other devices), consistency issues may appear due to data corruption or malicious intent. Since there is no central entity that can control the way information is spread and its correctness, alternative methods need to be employed. In this paper, we propose several mechanisms for ensuring data consistency in drop computing, ranging from a rating system to careful analysis of the data received. Through thorough experimentation, we show that our proposed solution is able to maximize the amount of correct (i.e., uncorrupted) data exchanged in the network, with percentages as high as 100%.
- ItemBlockchain-based platform for health data access management(IEEE, 2019) Hirtan, Liviu; Krawiec, Piotr; Dobre, Ciprian; Mongay Batalla, JordiBlockchain is a technology that offers the ability to create new business models and solves trust issues in a more efficient way. It can lead to many research opportunities and business innovations. Academia and industry proposed many blockchain based software solutions within a wide range of domains. In this paper we present a system design where blockchain technology is proposed to be used in the healthcare system, where the vital information regarding the medical analyses are shared between hospitals, medical clinics and research institutes based on access policies defined by the patients. In order to protect confidential data, our solution involves the use of two types of chains: a private one, the sidechain, which keeps information about real ID of the patients, and a public one, the mainchain, which stores information about patients' health data marked with a temporary ID. To test it, we developed the design using Hyperledger Fabric framework. Presented experimental results show good performance of the system in relation to the following metrics: 1) the time needed to identify the medical data for a particular patient, and 2) the mainchain propagation time of all the blocks within the peer to peer network.
- ItemClinically-validated INtegrated Support for Assistive Care and Lifestyle Improvement: the Human Link - vINCI - Preliminary Report on Clinical Architecture(2019) Herghelegiu, Anna Marie; Prada, Gabriel Ioan; Drăghici, Rozeta; Dobre, Ciprian; Rusu, Alexandra; Băjenaru, LidiaDigital technology has the potential to benefit the lives of older people, enabling them to live independently and providing the support to implement preventive health care, health education and promotion measures. The ViNCI project, funded under the Ambient Assisted Living programme, aims to develop an IoT-based eco-system technology constructed to offer a platform for early identification of health related problems. The most important feature of the ViNCI user-centric and privacy-aware technology is that the user is able to independently identify his/hers health risks and to receive direct feedback with specific recommendations. On an active screen tablet, seniors are able to self-complete a standardized questionnaire that assesses their quality of life across multiple domains. If their quality of life scores below the optimal level, evaluation of their psychological well-being and objective assessment of their physical activity level will be performed in a stepwise manner.
- ItemData fusion technique in spider peer-to-peer networks in smart cities for security enhancements(Elsevier, 2019-04) Mocanu, Bogdan; Pop, Florin; Mihaiţă Alexandra; Dobre, Ciprian; Castiglione, AnielloAn exciting piece of information was tweeted at the Microsoft Build 2017 conference, regarding the global Internet traffic. While, in 1992 the global Internet traffic was about 0.001 GB/s, today the global Internet traffic is estimated to 20,000 GB/s. This significant figure sets the plot for an interconnected environment that shares media content and sensors data. The most suitable environment for such a paradigm is a Smart-City. We present two data fusion techniques, which apply to the SPIDER Peer-to-Peer overlay.. The proposed methods take into consideration the architecture of the SPIDER overlay, which is formed by rings and chains; thus both chain and ring approaches are considered. Another contribution to this research is the analysis and presentation of two case scenarios of IoT in Smart Cities. The first scenario presents a novel approach to Smart-Streets and the second one describes a Waste recycling IoT scenario. The efficiency of the data fusion methods was evaluated through experimental data sets for different size neighborhoods.
- ItemDecentralized Storage System for Edge Computing(IEEE, 2019) Gheorghe, Alin-Gabriel; Crecana, Constantin-Cosmin; Negru, Cătălin; Pop, Florin; Dobre, CiprianWith the increases in mobile usage, data sensors and IoT devices the classical Cloud approach encounters a lot of problems in network congestion and in the response speed. A method for optimizing the communication between the devices and the cloud is to place the computing power in the proximity of sources. Edge Computing is a paradigm that proposes data processing and storage at the edge of the network. For the Mobile Edge Computing, the edge is represented by pervasive Radio Access Networks. Edge computing addresses a variety of applications and use cases. For instance, edge model can be used in Smart Cities, Cyber-physical infrastructures, Wireless Sensors and Actuators Networks. In the model, the tasks and the data are submitted first on the gateway nodes, which are devices with computation and storage capabilities. In this way the latency is minimized, and the network bandwidth is preserved. In this paper we present the design and evaluation of a novel decentralized storage system for Edge Computing paradigm aiming to provide a unified storage for data generated by different edge devices.
- ItemDepth-based human activity recognition: vINCI case study(IEEE, 2020) Băjenaru, Lidia; Dobre, Ciprian; Ciobanu, Radu-Ioan; Dedu, Georgiana; Pantelimon, Silviu-George; Marinescu, Ion Alexandru; Gavrilă, VeronicaThe growing aging of the world's population is leading to the need to take assistance measures and prepare health care systems for the elderly. The innovative vINCI system provides technologies and uses smart devices that can non-invasively monitor the activity of elderly, to intervene in case of alerts, to prevent possible health problems, such as falling, in the same time to keep their life independent and to improve their quality of life. Monitoring physical activity of the elderly with the help of smart cameras is important in identifying one of the most important lifestyle risk factors for many chronic conditions in the older age. In this paper there are presented the microservice-based vINCI architecture and how an Orbbec Persee camera is used to monitor the physical activity as well as to recognize the elderly. The advantages of the monitoring physical activity application consist in detecting a low level of activity or detecting health problems allowing intervention and correction of an unhealthy lifestyle.
- ItemDevice to Device Collaboration for Mobile Clouds in Drop Computing(IEEE, 2019) Marin, Radu-Corneliu; Gherghina-Pestrea Alexandru; Timisică, Alexandru Florin Robert; Ciobanu, Radu-Ioan; Dobre, CiprianThe large number of mobile devices existing nowadays has led to the evolution of mobile cloud computing towards bringing data and computations closer to the nodes. This has manifested first in the shape of fog and edge computing, where an additional communication and processing layer is added at the edge of the network. However, the fast adoption of the Internet of Things has shown the limitations of even this model, so the focus now is moving towards another layer that is one level below: the ad hoc network composed of the mobile devices themselves. One paradigm based on this model is Drop Computing, where nodes that need to do some computations first attempt to process them through the help of neighbor devices using close-range communication (such as Wi-Fi Direct or Bluetooth), and only then do they attempt to contact the fog/edge nodes or the cloud itself. In this paper, we propose an Android implementation of the device-to-device layer of Drop Computing. On top of this implementation, we present an application that creates a video collage from multiple photos using ffmpeg with the help of neighboring nodes through close-range communication using the HYCCUPS and Google Nearby frameworks. Through experiments on four Android devices, we show that our implementation can drastically decrease CPU usage per device, which in turn increases the overall quality of experience for Android users. Furthermore, the total battery consumption is lowered, since nodes have less computations to perform and the CPU cores spend less time in higher frequencies.
- ItemDrop computing: Ad-hoc dynamic collaborative computing(Elsevier, 2019-06) Ciobanu, Radu-Ioan; Negru, Cătălin; Pop, Florin; Dobre, Ciprian; Mavromoustakis, Constandions; Mastorakis, GeorgeMobile applications nowadays generally consist of a frontend component running on the device, and a backend component running on the cloud that performs the larger computations. However, this usage model leads to high costs for developing the application (since a cloud infrastructure that should scale to the number of users must be maintained), and to a potentially bad user experience (if the latency is high or the users employ mobile broadband they pay for). Thus, we introduce the Drop Computing paradigm, which proposes the concept of decentralized computing over multilayered networks, combining cloud and wireless technologies over a social crowd formed between mobile and edge devices. Mobile devices and people interconnect to form ad-hoc dynamic collaborations to support the equivalent of a crowd-based edge multilayered cloud of clouds, where the capabilities of any mobile device are extended beyond the local technology barriers, to accommodate external resources available in the crowd of other devices. Thus, instead of every data or computation request going directly to the cloud, Drop Computing employs the mobile crowd formed of devices in close proximity for quicker and more efficient access. Devices in the mobile crowd are leveraged for requesting already downloaded data or performing computations, and the cloud acts as the second (or even third) option. We present a proof-of-concept implementation of Drop Computing and show, through simulations, that it is feasible for real-life usage, since it is able to drastically reduce costs while not affecting or even improving the user experience.
- ItemEnhanced Living Environments: Algorithms, Architectures, Platforms, and Systems(Springer, 2019) Ganchev, Ivan; Garcia, Nuno; Dobre, Ciprian; Mavromoustakis, Constandinos; Goleva, Rossitza(Eds.)
- ItemEnhancing Scientific Collaborations using Community Detection and Document Clustering(IEEE, 2020) Rădulescu, Iulia Maria; Truică, Ciprian Octavian; Apostol, Elena Simona; Dobre, CiprianCommunity 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 clustering. Specifically, considering the clustering process, we use a sequence with proved performance between the WordNet lemmatizer, Document Embeddings and Spherical K-Means, while choosing the Louvain algorithm for community detection. Thus, we improve the Louvain's community detection algorithm modularity by interconnecting the author nodes for the articles clustered together. To evaluate our method, we collected a dataset containing articles' abstracts and authors. The experimental results show that our method suggests potential new collaborations by adding vertices to the graph after analysing the textual content.
- ItemGait Recognition as an Authentication Method for Mobile Devices(MDPI, 2020) Axente, Matei-Sorin; Dobre, Ciprian; Ciobanu, Radu-Ioan; Purnichescu-Purtan, RalucaWith the rate at which smartphones are currently evolving, more and more of human life will be contained in these devices. At a time when data privacy is extremely important, it is crucial to protect one’s mobile device. In this paper, we propose a new non-intrusive gait recognition based mechanism that can enhance the security of smartphones by rapidly identifying users with a high degree of confidence and securing sensitive data in case of an attack, with a focus on a potential architecture for such an algorithm for the Android environment. The motion sensors on an Android device are used to create a statistical model of a user’s gait, which is later used for identification. Through experimental testing, we prove the capability of our proposed solution by correctly classifying individuals with an accuracy upwards of 90% when tested on data recorded during multiple activities. The experiments, conducted on a low sampling rate and at short time intervals, show the benefits of our solution and highlight the feasibility of an efficient gait recognition mechanism on modern smartphones.
- ItemHow can we increase the quality of life in the elderly with neurocognitive disorders using vINCI technology(2019) Drăghici, Rozeta; Herghelegiu, Anna Marie; Prada, Gabriel Ioan; Rusu, Alexandra; Băjenaru, Lidia; Dobre, Ciprian; Ianculescu, Marilena; Marinescu, Ion Alexandru; Tomescu, Mihaela
- ItemHuman Physical Activity Recognition using Smartphone Sensors(MDPI, 2019-01-23) Voicu, Robert Andrei; Dobre, Ciprian; Băjenaru, Lidia; Ciobanu, Radu-IoanBecause the number of elderly people is predicted to increase quickly in the upcoming years, “aging in place” (which refers to living at home regardless of age and other factors) is becoming an important topic in the area of ambient assisted living. Therefore, in this paper, we propose a human physical activity recognition system based on data collected from smartphone sensors. The proposed approach implies developing a classifier using three sensors available on a smartphone: accelerometer, gyroscope, and gravity sensor. We have chosen to implement our solution on mobile phones because they are ubiquitous and do not require the subjects to carry additional sensors that might impede their activities. For our proposal, we target walking, running, sitting, standing, ascending, and descending stairs. We evaluate the solution against two datasets (an internal one collected by us and an external one) with great effect. Results show good accuracy for recognizing all six activities, with especially good results obtained for walking, running, sitting, and standing. The system is fully implemented on a mobile device as an Android application.
- ItemIdentifying the Needs of Older People for Personalized Assistive Solutions in Romanian Healthcare System(ICI, 2020-09-30) Băjenaru, Lidia; Marinescu, Ion Alexandru; Dobre, Ciprian; Drăghici, Rozeta; Herghelegiu, Anna Marie; Rusu, AlexandraThe new demographic perspectives lead to the necessity to develop new solutions based on the Internet of Things (IoT) technology, which is designed for the early identification of the health issues of the elderly people and for providing support to them so as to understand the factors that limit their Quality of Life (QoL). An adaptive technology, a personalized intervention and integrated wearable IoT devices have the potential to improve the national healthcare systems, especially the least developed ones, the efficacity of the provided services and thus, the QoL and the wellbeing of the elderly. This paper presents a user-oriented approach to the development of personalised assistive solutions in the field of elderly care, by identifying the needs and preferences of the older adults and translating them into development requirements of the vINCI platform, an ecosystem capable of providing a non-intrusive and personalised monitoring of physical and health parameters. In this regard, prior to the development of vINCI platform, two questionnaires were applied to a group of 62 participants aged 65 years or older without severe impairments, who were admitted as inpatients to “Ana Aslan” National Institute of Gerontology and Geriatrics in Bucharest and 62 formal and informal caregivers, with the purpose of identifying the needs of users. The vINCI technology aims to help the elderly people live independently and provides support for the implementation of preventive measures for healthcare.