Cristina Butca

Wearable sensors and cloud platform for monitoring environmental parameters in e-health applications

Wearable sensors enable long-term continuous physiological and environmental monitoring, which is important for the treatment and management of many chronic illnesses, neurological disorders, and mental health issues. In this paper we describe an experimental model based on wearable sensors, designed for monitoring the health condition of the patients. The system is based on a wearable sensor network connected to a cloud platform which aggregates the data received from the sensors. The sensors measure different parameters such as body temperature, humidity from the air, which are transmitted by microprocessor through a gateway to a cloud storage system. The data gathered in the cloud system is available for further processing, for the study of some correlations between measured parameters, environment conditions and health condition of the patients.

Big data fusion for eHealth and Ambient Assisted Living Cloud Applications

Senior citizens may suffer from a number of diseases, including but not limited to mild dementia and cognitive disabilities, which require either the institutionalization or the constant support from care-givers. To successfully help the senior citizens, usually a monitoring system is needed that can gather and process data from various sensors about the healthcare condition of the user and environment parameters (noise level, light, humidity and temperature). In this paper we describe a cloud-based approach for monitoring the healthcare condition of senior citizens and the fusion of big data from heterogeneous information flows coming from the sensors. Furthermore, because context understanding is not easily done with a single source of metadata, we analyze metadata available from various online sources, aiming to understand the context of its users, in order to offer them personalized eHealth services.

Rapid detection of pesticide residues based on telemetry platform

Pesticides are very important in improving agricultural production, but can harm beneficial insect species, soil, air, water, plants and their fruits. The purpose of this paper is to describe a telemetry solution together with a novel generation of immunobiosensors that will be used in order to gather data to a platform for remote monitoring of pesticide residues. The paper is an overview of the techniques and interfaces proposed for rapid detection of pesticide residues. LabVIEW is the preferred solution to create the graphical interface in order to insure the visualization of data. Furthermore, the platform can be applied for tele-monitoring pesticides in an agricultural production by performing a qualitative and quantitative assessment of pesticides. The paper fills a gap in the biosensors domain literature by proposing a solution based on data from immunobiosensors for rapid detection of pesticide through a telemetry platform.

Elastic disaster early warning system using a cloud-based communication center

An elastic early warning system enables people and authorities to save lives and property in case of disasters. In case of floods, a warning issued with enough time before the event will allow for reservoir operators to gradually reduce water levels, people to reinforce their homes, hospitals to be prepared to receive more patients, authorities to prepare and provide help. In this paper is presented an elastic disaster early warning system application that represents a “cloudified” early warning solution for natural disasters. The application collects data from real time sensors, processes the information, and provides warning services for the public. The system should be capable of collecting and processing the sensor data in nearly real time, and thus allowing very rapid response to urgent events. The main contribution of this paper consists in the presentation of the communication center with cloud computing clients that will be integrated with the early warning system.

Search based applications for speech processing

Nowadays, the demand for human-to-machine communication systems by using human voice is constantly growing. These systems allow the user to get access to information, fundament decisions and solve daily life or business issues in a timely and natural manner, with as little effort as possible. The complexity of the user input requested by many front-end speech recognition and back-end processing systems leads to imminent barriers when it comes to fulfilling a request. The main contribution of this paper consists in evaluating speech recognition solutions that support search engine integration. Furthermore, we propose an architecture for an intelligent speech-to-process platform using semantic analysis of natural language for processing the back-end orientations that can greatly benefit from search engine technologies.

Cloud platform for energy-aware resource management within SMEs

Environment concerns have gained more and more prevalence in the past decades, as better data and alarming prognosis regarding energy efficiency emerge from research. The private business sector already started to join the efforts with participation from both large companies and SMEs. Nowadays, in order to reduce energy costs and avoid penalties, companies concern themselves with an efficient use of tools and methodologies meant to help them monitor and manage resources. Smart solutions existing on the market allow organizations to gain control over the work environment through automatization and to maximize the comfort level of employees, while diminishing energy costs, following the principles of sustainable development. The purpose of this paper is to describe the methodologies and tools that can be integrated into a cloud platform, which will optimize the SMEs way to consume energy by providing them an overview of their consumption. Moreover, the papers presents the benefits that cloud platforms for energy-aware resource management can provide for SMEs and the main solutions which can be integrated in the field of building automation.

M2M sensors for Future Internet Of Things monitoring

Network monitoring represents an important factor in improving the quality of the services provided by communication networks. In this paper we describe a part of a network management and monitoring system that uses Machine-to-Machine (M2M) sensor systems, reducing costs through fast isolation of a subpart of the network that is not functional. The main contribution of this paper consists in the integration of data acquisition from the various equipments and sensors. Finally, the paper discusses the main findings for an implementation of M2M sensor systems for monitoring Digital Subscriber Lines (DSL) that provide access to Future Internet of Things (IoT) Networks.

Monitoring a cloud-based speech processing system

Currently, speech technology is used in various fields, such as: health care, military, telephony, education, aerospace research, telemetry, home automation, etc. This paper describes an experimental solution for synthesis and voice recognition which is adapted for use in Romanian language, and integrated with a call center application using the local network and a solution that allows users and providers to reduce the usage of the computational resources, conforming to the continually changing of business requirements inside an organization, by monitoring the systems and services offered by the cloud computing solution. The purpose of this paper is to propose a prototype communications system which integrates speech technology that makes interaction between customers / citizens and agents of contact center much easier. The main contribution of this paper is to describe the monitoring of a speech processing platform starting from a solution of “call / contact center” and the notification of security alerts by integrating a “text-to-speech” synthesizer in the Romanian language together with a “speech-to-text” application. Finally, the paper examines the main discoveries for a reference application of the monitoring system using the OpenStack cloud platform.

Cloud Search Based Applications for Big Data - Challenges and Methodologies for Acceleration

Innovation in Search Based Applications (SBAs) requires more than just creation of technology and use of Cloud Computing or Big Data (BD) platforms. Furthermore, the problem of acceleration in the aggregation and analysis of heterogeneous cloud-based data needs to be addressed. This paper fills a gap in the Cloud Computing literature by providing a general overview of the challenges and methodologies for acceleration of search applications for BD. The main contribution of this paper consists in analyzing cloud techniques that can be used for faster search of large volumes of data. Finally, the components and interfaces of the proposed SBA based on EXALEAD CloudView are presented and discussed.

Cloud and big data acceleration platform for innovation in environmental industry

Innovation in the environmental industry requires more than just creation of technology and use of cloud computing or big data platforms. It requires accelerated commercialization or aptly called go-to-market processes. To successfully accelerate, companies need a new type of product development, the so called validated learning process. Validated learning process systematically searches the fit between technology and market, by validating the mechanics of a business model. Acceleration consists in rapidly iterating between experiments, data collection, and informed decision making. However, every company needs to apply its own version of the validated learning process, focused on its context and industry. In this paper we describe a cloud platform that bring together several services and instruments that the companies usually rely on in their go-to-market process. The main contribution of this paper consists in analyzing the integration of big data sources in a cloud platform for accelerating the building, management and promotion of innovation in industry.