Activity detection is becoming an integral part of many mobile applications. Therefore, the algorithms for this purpose should be lightweight to operate on mobile or other wearable device, but accurate at the same time. In this paper, we... more
Activity detection is becoming an integral part of many mobile applications. Therefore, the algorithms for this purpose should be lightweight to operate on mobile or other wearable device, but accurate at the same time. In this paper, we develop a new lightweight algorithm for activity detection based on Long Short Term Memory networks, which is able to learn features from raw accelerometer data, completely bypassing the process of generating hand-crafted features. We evaluate our algorithm on data collected in controlled setting, as well as on data collected under field conditions, and we show that our algorithm is robust and performs almost equally good for both scenarios, while outperforming other approaches from the literature.
Research Interests:
Energy is the most important resource in state-of-the-art Internet of Things solutions. There are a lot of concepts and techniques dedicated to save energy, mainly focused to reduce transmission, since the energy used for preprocessing... more
Energy is the most important resource in state-of-the-art Internet of Things solutions. There are a lot of concepts and techniques dedicated to save energy, mainly focused to reduce transmission, since the energy used for preprocessing (encoding) is incomparable smaller than energy used for broadcasting. If applications do not require real-time measurements, data compression is one solution to energy saving problem. The goal of this paper was to develop new coding scheme for delta compression, that can be used for efficient data compression of temporally correlated data, such as temperature measurements coming from different smart devices. We proved that our coding scheme can achieve up to 85% energy saving. Compared to other coding techniques, our scheme has greater compression ratio and lower memory requirements.
Research Interests: Sensors and Sensing, Data Compression, The Internet of Things, Wireless Sensor Networks, Internet of Things, and 19 moreWSN (Wireless sensor network), Temperature Sensors, Sensor networks, Wireless Sensor Networks (WSN), Big Data, Huffman Encoding, Data Reduction, Wireless Sensor Networks (WSNs), Data Compression algorithms., Data Reduction Software, Internet of Things (IoT), IOT, Data Reduction by Huffmann Coding and Encryption by Insertion of Shuffled Cyclic Redundancy Code, Energy Efficiency in WSN, wireless applications with Internet of Thing (IoT) within Internet environment, Adaptive Delta Modulation, LZW algorithm, Data Encoding Techniques for Reducing Power Consumption in Network on Chips, and Electronics and Communications Engineering Computer Networks Tcp/Ip Internet of Things
IoT systems are expected to generate voluminous raw sensor measurements that require high bandwidths to be transmitted to the clouds. IoT data prediction is one solution to this issue. Yet, many algorithms based on different models for... more
IoT systems are expected to generate voluminous raw sensor measurements that require high bandwidths to be transmitted to the clouds. IoT data prediction is one solution to this issue. Yet, many algorithms based on different models for times series prediction can be used for this purpose. IoT developers have to choose among many of them, since they perform differently for different sensor measurements. In this paper, we present DAta Prediction System (DAPS), a web-based online tool that helps IoT developers to choose the most suitable data prediction algorithms for their application.
Research Interests: Sensors and Sensing, The Internet of Things, Wireless Sensor Networks, Internet of Things, WSN (Wireless sensor network), and 20 moreSensors, Smart Cities, Wireless Sensor Networks (WSN), Smart City, Big Data, Data Reduction, Multi Sensor Data Fusion, Wireless Sensor Networks (WSNs), Data Reduction Software, Internet of Things (IoT), IOT, Data Integration benefits to smart cities, Energy Efficiency in WSN, RFID and Sensor Networks, Smart Green City, Fog Computing, Industrial Internet of Things, Data Encoding Techniques for Reducing Power Consumption in Network on Chips, Application of Fog Computing in Internet of Things, and dew computing
Smart grid is the process of applying ICT in order to optimize energy consumption and decrease energy loses. This paper presents a three tier Internet of Thing based hierarchical framework for the smart home, as a reflection to the... more
Smart grid is the process of applying ICT in order to optimize energy consumption and decrease energy loses. This paper presents a three tier Internet of Thing based hierarchical framework for the smart home, as a reflection to the present lack of intelligent solutions that do not fully use the advantages of Internet of Thing technologies. Our framework aims to extend the smart home to microgrid level, in order to integrate all renewable distributed energy sources from the microgrid and to achieve better energy optimization. As an extension to the traditional data processing, we define fog computing approach for smart home. Through simulation on real smart meter dataset, we showed that fog computing based on predictive filters can reduce the number of transmissions and minimize smart home network traffic.
Research Interests: The Internet of Things, Internet of Things, Smart Grid and Intelligent Micro Grid, Smart Grid, Microgrid, and 24 moreSmart grids, Smart Home Technology, Smart Cities, Smart City, Smart Home, Smart Homes, Data Reduction, SmartGrids, Internet of Things (IoT), GSM Based Electrical Control System for Smart Home Application, Smart and Knowledge cities, Smart house, Signal Compression Technique in Smart Grid, Microgrids, Microgrids and Smart Grids, Smart Houses, Renewables Integration Into Smart Grid, Smart Green City, Smart City Research, Fog Computing, Application of Fog Computing in Internet of Things, Internet of Things, Parallel & Distributed Systems (Focus on Cloud & Edge/Fog Computing, Big Data and Social Networks) and Data Mining, Edge Computing, and dew computing
One of the key challenges in the ever-changing ubiquitous computing environment of Internet of Things is accurate determination of each of its' elements location. Indoor localization for smartphones has been in line with this research... more
One of the key challenges in the ever-changing ubiquitous computing environment of Internet of Things is accurate determination of each of its' elements location. Indoor localization for smartphones has been in line with this research initiatives in the last decade, along with the inherited background from wireless sensor networks perspective. Therefore, most of the algorithms from the literature are based on distance measurements obtained from radio signal strength ranging technique and evaluated mostly through simulations. In this paper, we experimentally evaluated a well-known technique for localization based on multidimensional scaling, using different models of smartphones. Additionally, we analyzed the behavior of the signal strength measured by the smartphones under different field condition. From our results, we concluded that radio signal strength indicator should be combined with more accurate ranging techniques into hybrid solutions to be used for indoor localization of smartphones.
Research Interests:
Research Interests:
—Technology enhanced education has been recently established as a new approach for all stages of education in developing countries, especially in Macedonia. Although computer games are often given little attention we believe that within... more
—Technology enhanced education has been recently established as a new approach for all stages of education in developing countries, especially in Macedonia. Although computer games are often given little attention we believe that within the vast amount of technologies and instruments used to achieve the needed improvements it is computer games that are playing the central role in delivering the desired effects, in particular to children and teenagers. In this paper we present the " Toby the Explorer " , an interactive educational game for primary school students. We show in depth the engineering behind the game, its design and structure. We also give an insight and evaluation of the importance of the game in enhancing the educational process. Our results show that the learning process is regarded as more easy and fun by the students that learned by playing, but also it increased their interest in learning other subjects not included explicitly in the game.
Research Interests:
Although Internet of Things (IoT) brings significant advantages over traditional communication technologies for smart grid and smart home applications, these implementations are still very rare. Relying on a comprehensive literature... more
Although Internet of Things (IoT) brings significant advantages over traditional communication technologies for smart grid and smart home applications, these implementations are still very rare. Relying on a comprehensive literature review, this paper aims to contribute towards narrowing the gap between the existing state-of-the-art smart home applications and the prospect of their integration into an IoT enabled environment. We propose a holistic framework which incorporates different components from IoT architectures/frameworks proposed in the literature, in order to efficiently integrate smart home objects in a cloud-centric IoT based solution. We identify a smart home management model for the proposed framework and the main tasks that should be performed at each level. We additionally discuss practical design challenges with emphasis on data processing, as well as smart home communication protocols and their interoperability. We believe that the holistic framework ascertained in this paper can be used as a solid base for the future developers of Internet of Things based smart home solutions.
Research Interests: The Internet of Things, Future Internet Architecture, Internet of Things, Survey Research (Research Methodology), Smart Grid and Intelligent Micro Grid, and 32 moreFuture Internet, Smart Grid, Cloud Computing, Network Protocols and Architectures, 6LoWPAN, Interoperability, Smart grids, Smart Home Technology, Smart City, Smart Home, Energy Efficient Protocols in Wireless Sensor Networks, Smart Homes, SmartGrids, ZigBee, Internet of Things (IoT), GSM Based Electrical Control System for Smart Home Application, Electrical Power Distribution Network Optimization with Distributed Generation and Smartgrids, Device-to-Device Communication, Methodology and Review of Related Literature, IOT, Microgrids and Smart Grids, wireless applications with Internet of Thing (IoT) within Internet environment, M2m Communication, Smart Green City, IoT/M2M, Smart City with Internet of Things, Z-Wave, Internet of Things (IoTs), Fog Computing, Machine-to-Machine (M2M) communications, Electronics and Communications Engineering Computer Networks Tcp/Ip Internet of Things, and Application of Fog Computing in Internet of Things
—Localization in Wireless Sensor Networks (WSNs) has been a challenging problem in the last decade. The most explored approaches for this purpose are based on multidimensional scaling (MDS) technique. The first algorithm that introduced... more
—Localization in Wireless Sensor Networks (WSNs) has been a challenging problem in the last decade. The most explored approaches for this purpose are based on multidimensional scaling (MDS) technique. The first algorithm that introduced MDS for nodes localization in sensor networks is well known as MDS-MAP. Since its appearance in 2003, many variations of MDS-MAP have been proposed in the literature. This paper aims to provide a comprehensive survey of the localization techniques that are based on MDS. We classify MDS-based algorithms according to different taxonomy features and different evaluation metrics.
Research Interests:
Research Interests:
Research Interests:
Pervasive and ubiquitous computing are expected to expend the development of new business oriented mobile applications. Knowing the exact physical location of the wireless devices is crucial for providing awareness of these applications.... more
Pervasive and ubiquitous computing are expected to expend the development of new business oriented mobile applications. Knowing the exact physical location of the wireless devices is crucial for providing awareness of these applications. Many algorithms have been proposed for wireless localization, but most of them are designed for outdoor localization by using Global Positioning System (GPS) signals. In indoor environments where GPS is not available localization becomes complex and challenging task. It is also a challenge to cope with reflection, diffraction or absorption of the radio signals, as well as to include many other characteristics like temperature and humidity variations, orientation of antennas, presence of furniture and human beings, which causes localization inaccuracy in indoor environments. INLOC aims to develop new comprehensive set of methodologies and analysis tools for indoor GPS free wireless mobile positioning and navigation including contextual information ab...
With the expected growth in world population, demand on energy would continuously increase. Smart grid is a new concept that integrates information and communication technologies (ICT) with grid power systems in order to achieve efficient... more
With the expected growth in world population, demand on energy would continuously increase. Smart grid is a new concept that integrates information and communication technologies (ICT) with grid power systems in order to achieve efficient and intelligent energy generation and consumption. The new advanced concepts, such as Pervasive or Ubiquitous computing, where computing is made to appear everywhere and anywhere, impose huge potential to be integrated into smart grid application. Wireless sensor networks (WSN) composing of home appliances and smart gadgets, if combined with smart metering, can transform residential houses, homes and offices into energy-aware environments. Using intelligent power scheduling algorithms, residents would be able to make optimal a priory choices about how to spent electricity in order to decrease energy consumption. On the other hand, utilities would benefit as load demand would be shedded in critical situations. In this paper, the potential of the sta...
Pervasive and ubiquity computing produce huge amount of sensed data that need to be transmitted through the network, stored and processed at the server side, thus imposing huge ICT power consumption, both for transmitting and processing.... more
Pervasive and ubiquity computing produce huge amount of sensed data that need to be transmitted through the network, stored and processed at the server side, thus imposing huge ICT power consumption, both for transmitting and processing. In order to minimize the cost, dozens of solutions have been proposed, with focs of network protocols and architectures, as well as database searching techniques for big data. EFICOM aims to develop new comprehensive set of methodologies and analysis tools for energy efficient green communication and networking, by using intelligent mechanisms that reduce the number of transmissions in the network, but without losing the essential information. By using data prediction paradigms and spatio-temporal correlations among the sources, these techniques should focus on cooperative in-network knowledge extraction, rather than retransmitting the raw data. This approach should be especially desirable for networks dedicated to environmental monitoring, smart gr...
In the recent years, there has been a huge advancement in wireless sensor computing technology. Today, wireless sensor network (WSN) has become a key technology for different types of smart environment. Nodes localization in WSN has... more
In the recent years, there has been a huge advancement in wireless sensor computing technology. Today, wireless sensor network (WSN) has become a key technology for different types of smart environment. Nodes localization in WSN has arisen as a very challenging problem in the research community. Most of the applications for WSN are not useful without a priory known nodes positions. Adding GPS receivers to each node is an expensive solution and inapplicable for indoor environments. In this paper, we implemented and evaluated an algorithm based on multidimensional scaling (MDS) technique for three-dimensional (3D) nodes localization in WSN using improved heuristic method for distance calculation. Using extensive simulations we investigated our approach regarding various network parameters. We compared the results from the simulations with other approaches for 3D-WSN localization and showed that our approach outperforms other techniques in terms of accuracy.
Research Interests:
Wireless sensor networks take a major part in our everyday lives by enhancing systems for home automation, healthcare, temperature control, energy consumption monitoring, and so forth. In this paper we focus on a system used for... more
Wireless sensor networks take a major part in our everyday lives by enhancing systems for home automation, healthcare, temperature control, energy consumption monitoring, and so forth. In this paper we focus on a system used for temperature regulation for residential, educational, industrial, and commercial premises, and so forth. We propose a framework for indoor temperature regulation and optimization using wireless sensor networks based on ZigBee platform. This paper considers architectural design of the system, as well as implementation guidelines. The proposed system favors methods that provide energy savings by reducing the amount of data transmissions through the network. Furthermore, the framework explores techniques for localization, such that the location of the nodes can be used by algorithms that regulate temperature settings.
Research Interests:
Following the latest developments in computer and communication technologies, everyday objects are becoming smarter, as ubiquitous connectivity and modern sensors allow them to communicate with each other. The deployment of sensors and... more
Following the latest developments in computer and communication technologies, everyday objects are becoming smarter, as ubiquitous connectivity and modern sensors allow them to communicate with each other. The deployment of sensors and actuators everywhere around us adds a new dimension to the world of information and communication, which enables the creation of new and enriched services widely applied in different industrial and civilian application areas.
The aim of this thesis is to develop data fusion strategies for Wireless Sensor Networks (WSN) that remove temporal or spatial redundancies between sensor measurements in order to decrease the network load. In context of spatial data fusion, nodes localization appears as the first problem to be solved in order to find spatial correlation between data from neighboring nodes. In this thesis two approaches were purposed, implemented and evaluated for solving three dimensional WSN localization problems. In context of temporal data fusion, different techniques for data reduction based of time series forecasting were analyzed, implemented and evaluated. From the evaluation of the algorithms it can be concluded that star network is the most suitable network topology by means of energy saving. If sensors are not within each other radio range, cluster-based topology could be used. Additionally, if data aggregation is applied at cluster head, this topology can achieve even greater data reduction in scenarios where loosing data precision is affordable.
The aim of this thesis is to develop data fusion strategies for Wireless Sensor Networks (WSN) that remove temporal or spatial redundancies between sensor measurements in order to decrease the network load. In context of spatial data fusion, nodes localization appears as the first problem to be solved in order to find spatial correlation between data from neighboring nodes. In this thesis two approaches were purposed, implemented and evaluated for solving three dimensional WSN localization problems. In context of temporal data fusion, different techniques for data reduction based of time series forecasting were analyzed, implemented and evaluated. From the evaluation of the algorithms it can be concluded that star network is the most suitable network topology by means of energy saving. If sensors are not within each other radio range, cluster-based topology could be used. Additionally, if data aggregation is applied at cluster head, this topology can achieve even greater data reduction in scenarios where loosing data precision is affordable.
Research Interests:
ABSTRACT In the recent years, there has been huge advancement in wireless sensor computing technology. Today, Wireless Sensor Network (WSN) has become a key technology for different types of smart environment. Nodes localization in WSN... more
ABSTRACT
In the recent years, there has been huge advancement in wireless sensor computing technology. Today, Wireless Sensor Network (WSN) has become a key technology for different types of smart environment. Nodes localization in WSN has arisen as a very challenging problem in the research community. Most of the applications for WSN are not useful without a priory known nodes positions. Adding GPS receivers to each node is an expensive solution and inapplicable for indoor environments. In this paper, we implemented and evaluated improved MDS-MAP algorithm for three dimensional (3D) nodes localization in WSN. Using extensive simulations we investigated our approach regarding various network parameters. We compared the results from the simulations with other approaches for 3D-WSN localization and showed that our algorithm outperforms other techniques in terms of accuracy.
In the recent years, there has been huge advancement in wireless sensor computing technology. Today, Wireless Sensor Network (WSN) has become a key technology for different types of smart environment. Nodes localization in WSN has arisen as a very challenging problem in the research community. Most of the applications for WSN are not useful without a priory known nodes positions. Adding GPS receivers to each node is an expensive solution and inapplicable for indoor environments. In this paper, we implemented and evaluated improved MDS-MAP algorithm for three dimensional (3D) nodes localization in WSN. Using extensive simulations we investigated our approach regarding various network parameters. We compared the results from the simulations with other approaches for 3D-WSN localization and showed that our algorithm outperforms other techniques in terms of accuracy.
Research Interests:
Wireless communication itself consumes the most amount of energy in a given WSN, so the most logical way to reduce the energy consumption is to reduce the number of radio transmissions. To address this issue, there have been developed... more
Wireless communication itself consumes the most amount of energy in a given WSN, so the most logical way to reduce the energy consumption is to reduce the number of radio transmissions. To address this issue, there have been developed data reduction strategies which reduce the amount of sent data by predicting the measured values both at the source and the sink, requiring transmission only if a certain reading differs by a given margin from the predicted values. While these strategies often provide great reduction in power consumption, they need a-priori knowledge of the explored domain in order to correctly model the expected values. Using a widely known mathematical apparatus called the Least Mean Square Algorithm (LMS), it is possible to get great energy savings while eliminating the need of former knowledge or any kind of modeling. In this paper with we use the Least Mean Square Algorithm with variable step size (LMS-VSS) parameter. By applying this algorithm on real-world dataset, we achieved maximum data reduction of over 95 % for star topology and around 97 % when data aggregation was taken into account for cluster-based topology, both for error margin of 0.5 °C. Using mean square error as metric for evaluation, we show that our algorithm outperforms classical LMS technique.
Research Interests:
With the recent development of technology, wireless sensor networks (WSN) are becoming an important part of many applications. Knowing the exact location of each sensor in the network is very important issue. Therefore, the localization... more
With the recent development of technology, wireless sensor networks (WSN) are becoming an important part of many applications. Knowing the exact location of each sensor in the network is very important issue. Therefore, the localization problem is a growing field of interest. Adding GPS receivers to each sensor node is costly solution and inapplicable on nodes with limited resources. Additionally, it is not suitable for indoor environments. In this paper, we propose an algorithm for nodes localization in WNS based on multidimensional scaling (MDS) technique. Our approach improves MDS by distance matrix refinement. Using extensive simulations we investigated in details our approach regarding different network topologies, various network parameters and performance issues. The results from simulations show that our improved MDS (IMDS) algorithm outperforms well known MDS-MAP algorithm [1] in terms of accuracy.
Research Interests:
Nodes localization in Wireless Sensor Networks (WSN) has arisen as a very challenging problem in the research community. Most of the applications for WSN are not useful without a priori known nodes positions. One solution to the problem... more
Nodes localization in Wireless Sensor Networks (WSN) has arisen as a very challenging problem in the research community. Most of the applications for WSN are not useful without a priori known nodes positions. One solution to the problem is by adding GPS receivers to each node. Since this is an expensive approach and inapplicable for indoor environments, we need to find an alternative intelligent mechanism for determining nodes location. In this paper, we propose our cluster-based approach of multidimensional scaling (MDS) technique. Our initial experiments show that our algorithm outperforms MDS-MAP[8], particularly for irregular topologies in terms of accuracy.
Research Interests: Clusters & Networks, Multidimensional Scaling, Indoor Positioning, Localization, Localization (Computer Science), and 8 moreLocalization in WSN, WSN (Wireless sensor network), Localisation, Indoor Localization, Internet of Things (IoT), Positioning, INDOOR POSITIONING SYSTEM, and Sensor Networks and IoT
Research Interests:
Research Interests:
With the recent development of technology, wireless sensor networks are becoming an important part of many applications such as health and medical applications, military applications, agriculture monitoring, home and office applications,... more
With the recent development of technology, wireless sensor networks are becoming an important part of many applications such as health and medical applications, military applications, agriculture monitoring, home and office applications, environmental monitoring, etc. Knowing the location of a sensor is important, but GPS receivers and sophisticated sensors are too expensive and require processing power. Therefore, the localization wireless sensor network problem is a growing field of interest. The aim of this paper is to give a comparison of wireless sensor network localization methods, and therefore, multidimensional scaling and semidefinite programming are chosen for this research. Multidimensional scaling is a simple mathematical technique widely-discussed that solves the wireless sensor networks localization problem. In contrast, semidefinite programming is a relatively new field of optimization with a growing use, although being more complex. In this paper, using extensive simulations, a detailed overview of these two approaches is given, regarding different network topologies, various network parameters and performance issues. The performances of both techniques are highly satisfactory and estimation errors are minimal.
Research Interests:
Traditional teaching, usually based on lectures and tutorials fosters the idea of instruction-driven learning model where students are passive listeners. Besides this approach, Project Based Learning (PBL) as a different learning... more
Traditional teaching, usually based on lectures and tutorials fosters the idea of instruction-driven learning model where students are passive listeners. Besides this approach, Project Based Learning (PBL) as a different learning paradigm is standing behind constructivism learning theory, where learning from real-world situations is put on the first place.
The purpose of this paper is to present our approach in learning embedded systems at our University. It is based on combination of traditional (face-to-face) learning and PBL. Our PBL represents an interdisciplinary project based on wireless sensor monitoring of real-world environment (greenhouse). The students use UML that was shown as an excellent tool for developing such a projects. From the student perspective, we found that this high level of interdisciplinary is very valuable from the point of view of facing the students with real-life problems.
The purpose of this paper is to present our approach in learning embedded systems at our University. It is based on combination of traditional (face-to-face) learning and PBL. Our PBL represents an interdisciplinary project based on wireless sensor monitoring of real-world environment (greenhouse). The students use UML that was shown as an excellent tool for developing such a projects. From the student perspective, we found that this high level of interdisciplinary is very valuable from the point of view of facing the students with real-life problems.