Theodore A. Tsiligiridis

Adaptive design optimization of wireless sensor networks using genetic algorithms

We present a multi-objective optimization methodology for self-organizing, adaptive wireless sensor network design and energy management, taking into consideration application-specific requirements, communication constraints and energy-conservation characteristics. A precision agriculture application of sensor networks is used as an example. We use genetic algorithms as the optimization tool of the developed system and an appropriate fitness function is developed to incorporate many aspects of network performance. The design characteristics optimized by the genetic algorithm system include the status of sensor nodes (whether they are active or inactive), network clustering with the choice of appropriate clusterheads and finally the choice between two signal ranges for the simple sensor nodes. We show that optimal sensor network designs constructed by the genetic algorithm system satisfy all application-specific requirements, fulfill the existent connectivity constraints and incorporate energy-conservation characteristics. Energy management is optimized to guarantee maximum life span of the network without lack of the network characteristics that are required by the specific application.

Energy optimization of wireless sensor networks for environmental measurements

In this paper we propose an approach to op t im al design of application-specific wireless sen so r networks based on th e optim ization prop erties of genetic algorithm s. S p eci fi c requirem en ts fo r a precision agriculture applicatio n of sen so r networks are taken in t o a cco u nt by the genetic algo rithm system , together with connectivity an d en erg y co n s erva t i on lim ita tions. We d evel o p an appropriate fitness function to inco rporate many aspects of network performance. The design characteristics optim ized by the genetic algorithm system includ e the sta tu s of sen so r nodes (whether they are active or inactive), network clustering with the ch o i ce of app ro p r ia t e cl u st erh ea d s and fina lly the ch o i ce b et w een two signal ran g es fo r the norm al sen so r nodes. Op tim a l sen so r network designs co nstructed by the genetic algo rithm system satisfy al l application-specific req u irem en ts, fulfill th e ex istent connectivity co nstraints and inco rporate en erg y co n s erva t i o n characteristics.

A memetic algorithm for optimal dynamic design of wireless sensor networks

We present a memetic algorithm that dynamically optimizes the design of a wireless sensor network towards energy conservation and extension of the life span of the network, taking into consideration application-specific requirements, communication constraints and energy consumption of operation and communication tasks of the sensors. The memetic algorithm modifies an already successful genetic algorithm design system and manages to improve its performance. The obtained optimal sensor network designs satisfy all application-specific requirements, fulfill the existing connectivity constraints and incorporate energy conservation characteristics stronger than those of the original genetic algorithm system. Energy management is optimized to guarantee maximum life span of the network without lack of the network characteristics that are required by the specific sensing application.

Feature extraction for time-series data: An artificial neural network evolutionary training model for the management of mountainous watersheds

The present manuscript is the result of research conducted towards a wider use of artificial neural networks in the management of mountainous water supplies. The novelty lies on the evolutionary clustering of time-series data which are then used for the training and testing of a neural object, applying meta-heuristics in the neural training phase, for the management of water resources and for torrential risk estimation and modelling. It is essentially an attempt towards the development of a more credible forecasting system, exploiting an evolutionary approach used to interpret and model the significance which time-series data pose on the behavior of the aforementioned environmental reserves. The proposed model, designed such as to effectively estimate the average annual water supply for the various mountainous watersheds, accepts as inputs a wide range of meta-data produced via an evolutionary genetic process. The data used for the training and testing of the system refer to certain watersheds spread over the island of Cyprus and span a wide temporal period. The method proposed incorporates an evolutionary process to manipulate the time-series data of the average monthly rainfall recorded by the measuring stations, while the algorithm includes special encoding, initialization, performance evaluation, genetic operations and pattern matching tools for the evolution of the time-series into significantly sampled data.

Evolutionary energy management and design of wireless sensor networks

We present an evolutionary optimization methodology for self-organizing, adaptive wireless sensor network design and energy management, taking into consideration application- specific requirements, communication constraints and energy conservation characteristics. A precision agriculture application of sensor networks is used as an example. We use genetic algorithms as the optimization tool of the developed system and an appropriate fitness function is developed to incorporate many aspects of network performance. The design characteristics optimized by the genetic algorithm system include the status of sensor nodes (whether they are active or inactive), network clustering with the choice of appropriate clusterheads and finally the choice between two signal ranges for the regular sensor nodes. We show that optimal sensor network designs constructed by the genetic algorithm system satisfy all application-specific requirements, fulfill the existent connectivity constraints and incorporate energy conservation characteristics. Energy management is optimized to guarantee maximum life duration of the network without lack of the required by the specific application network characteristics.

Piecewise evolutionary segmentation for feature extraction in time series models

The design, development and implementation of an innovative system utilized in feature extraction from time series data models is described in this manuscript. Achieving to design piecewise segmentation patterns on the time series in an evolutionary fashion and use them in order to produce fitter secondary data sets, the developed system adapts itself to the nature of the problem each time and finally elects an optimally parameterized classifier (artificial neural network or support vector machine), along with the fittest time series segmentation pattern. The application of the system onto two different problems involving time series data analysis and requiring predictive and classification capabilities (torrential risk assessment and plant virus identification, respectively), reveals that the proposed methodology was crucial in finding the optimum solution for both problems. Piecewise evolutionary segmentation time series model analysis, utilized by the accompanying software tool, succeeded in controlling the dimensionality and noise inherent in the initial raw time series information. The process eventually proposes a segmentation pattern for each problem, enhancing the potential of the corresponding classifier.

Designing CSCW system for integrated, web-based, cotton cultivation services

Computer Supported Collaborative Work (CSCW) systems have attracted the attention of many software implementers on the area of multimedia applications, however very few of them have been used in agriculture. The necessity for using the CSCW environment in agriculture arises from the utilization and the rapid development of modern strategies of plant cultivation. In this paper we present the design of an agricultural CSCW system, which aims to provide integrated, web-based, services for cotton cultivation. Designing and developing such a system is a complex task that requires dealing with a great number of challenges. We focused on a number of important interrelated issues of user profiles, providing an overview and an insight on the way we address them. The proposed framework is intended to contribute to a unified view of requirements of a knowledge management support system by identifying core components and functionalities.

Performance Optimization of a Clustering Adaptive Gravitational Search Scheme for Wireless Sensor Networks

In this research we propose a new clustering scheme based on a combination of a well known stochastic, population-based Gravitational Search Algorithm (GSA) and the k-means algorithm to select optimal reference nodes in a Wireless Sensor Networks (WSN). In the proposed scheme the process of grouping sensors into clusters reference nodes is based on a K-means clustering algorithm to divide the initial population and select the best position in the neighbourhood to exchange information between clusters. In cases when sensor nodes receive multiple synchronization messages from more than one reference node a weighted average method is used. In this paper we limit our research on a number of benchmark functions which are used to compare the performance of the proposed algorithm with other important meta-heuristic algorithms to show its superiority.

A Middleware for Managing Sensory Information in Pervasive Environments

Context and context-aware computing have attracted remarkable attention in recent years. Research into wireless sensor networks is rapidly moving from simulations to realistic testbeds. The work presented here investigates the architecture and design of an agent-based sensor network for monitoring and spraying control of olive fly in an ubiquitous precision farming environment. It contributes by providing a generic, flexible and extensible model for handling heterogeneous sensor data, which can be managed using a simple user interface. The innovative aspect stands for the development of a multi-agent system and focuses on the communication aspects of the proposed middleware architecture. The modeling allows the encapsulation of different modules as agents and integrates them, by utilizing a standardized XML schema in order to hide complexity to the users. The proposed design adopts a layered architecture, which is based on some software agents that solve different tasks and communicate among themselves their results and requests

Multi-criteria Optimization Methods Applied in Agricultural Touring

Agricultural tourism is considered a means of providing motor for growth in rural areas and year-round tourism flow, promoting local products and SMEs, encouraging the diversification of economic activity and in the long run a way of improving the quality of life in rural areas. For more than three decades now this concept goes hand to hand with avoiding/preventing the social and economic collapse of rural areas, and with multi-functionality. Ιncreasing interest in tourism, tourism in rural areas and thematic tourism as well as tourists seeking fast and accurate information has led to the proposal of personalized (team) tours, rather than generic ones, with the use of recommender and geo-informatic systems alongside with smart applications, web services, context and location based services. Τo provide maximum functionality to users and engage them into using a service it is needed to represent/model the real daily multi-dimensional activities of a tourist during a trip with more than one objective function. Crucial to such a service are the formulations that model tourist trip problems, and the algorithms that generate and optimize the proposed tours. Therefore, this comprehensive review explores the multi-objective nature of agricultural touring, and focuses on multi-objective formulations that arose in the literature so far in touring, especially concerning tourism, and in regard of them being applied under agri-touristical scenarios. Under the scope of multi-objective optimization, we focus also in the related Orienteering and Team Orienteering Problem (OP/TOP). We consider selected non-dynamic/dynamic multi-objective route planning problems/methods, variants of the OP and TOP for route planning and scheduling problems, as well as for tourism and agricultural tourism, and the algorithms proposed and/or tested for the latter.