Constantine P. Yialouris

DIARES-IPM: a diagnostic advisory rule-based expert system for integrated pest management in Solanaceous crop systems

Abstract This paper presents a DIagnostic Advisory Rule-based Expert System for Integrated Pest Management (DIARES-IPM) in Solanaceous crops. DIARES-IPM is an operational automatic identification tool that helps non-experts to identify pests (insects, diseases, nutritional deficiencies and beneficial insects) and suggest the appropriate treatments. The objective of this expert system was to serve as a diagnostic, extension and educational tool in vegetable IPM and it includes the most economically important diseases, insects (noxious and beneficial insects) and nutritional deficiencies that affect these crops. All the diagnostic knowledge is contained in an integrated knowledge base. This is of great importance for IPM, in which all the pests are to be taken into account if an appropriate management strategy is to be applied. The methodology can also be applied to other vegetable crops without needing to rewrite the core knowledge base, while the overall system design, with minor changes, could be applicable to pest diagnosis or pest risk assessment in any other agro-ecosystem. To implement DIARES-IPM, EXSYS tool for Windows was used and the knowledge is represented in the linguistic form of IF-THEN rules. The expert system has been evaluated following conventional expert system evaluation methodologies.

A diagnostic expert system for honeybee pests

Abstract This paper describes the development of a rule-based expert system to diagnose pests of honeybees (Apis mellifera L.) and to suggest the appropriate treatments. The system can be used as a diagnostic tool for beekeepers and as for educational and extension purposes in bee pathology. It provides a diagnosis based on the description of the external appearance or behavior of the affected colony. Corresponding pictures accompany the most important symptoms and certain measures to be taken are proposed. The expert system was evaluated following the conventional expert system evaluation methodologies. The system was implementing using exsys for Microsoft Windows environment.

An expert system for tomato diseases

Abstract In this paper an expert system (ES) for tomato diseases identification is presented. Problems related to knowledge acquisition and knowledge representation procedures are dealt with, employing techniques which can also be used to develop diagnostic ES for other types of plants. The system is based on a recently developed shell which allows the manipulation of the corresponding knowledge base as a database. Thus, the user interface of the system is enhanced with additional capabilities.

Insect identification expert system for forest protection

A forest can be considered as the major component of an ecosystem since it plays a critical role in soil protection, air quality, flood reduction, etc. It also plays a significant economic role for rural areas and for the national economy as a whole. The forests health depends on many factors, such as biological, physical and anthropogenic. During recent decades, however, its health weakens continuously, because of the extreme meteorological phenomena and the increase of wildfires. As a consequence, the forests sensitivity to secondary attacks by insects and fungus increases rapidly, since the latter find convenient expansion conditions. In this paper, an Expert System (ES) is described which identifies forest insects and proposes relevant treatment. It can identify more than forty distinct insects, either from some stage of their lifecycle or from the damage they cause to trees or from the findings that they leave in the forest. Once an insect identification is completed, the system can recommend an appropriate treatment, aiming at reducing spread of insects in the whole forest and at minimizing possible forest damage. The system is enhanced with photos and drawings that assist the user in the precise and quick identification of an insect. It can be used by unspecialised personnel or inexperienced users, such as forest owners. It can also be used in education or for training purposes, as a simple tutoring system. One major advantage of the ES is that it integrates, in, a single module, knowledge from diverse areas.

Time-evolving rule-based knowledge bases

Abstract Human knowledge in any expertise area changes with respect to time. Two types of such knowledge can be identified, time independent and time dependent . It is shown that the maintenance effort of the latter is harder than that of the former. The present paper applies research results in the area of temporal databases, in order to maintain a rule-based knowledge base whose content changes with respect to the real world time. It is shown that the approach simplifies the maintenance of time dependent knowledge. It also enables the study of the evolution of knowledge with respect to time, which is knowledge on its own . Three distinct solutions are actually proposed and evaluated. Their common characteristic is that knowledge is stored in a database; therefore, all the advantages of databases are inherited by knowledge bases. Implementations are also reported.

VEGES—A multilingual expert system for the diagnosis of pests, diseases and nutritional disorders of six greenhouse vegetables

Simple, plastic covered greenhouses are used widely in the Mediterranean basin for the production of out of season vegetables such as aubergine, bean, cucumber, lettuce, pepper and tomato, which account for over 50% (Spain and Italy) and 90% (Greece) of the total area of such greenhouses. Despite the economic importance of this greenhouse industry to the region, its low technology (LT) status has so far failed to attract the attention of the high technology (HT) software industry and in consequence, appropriate, low cost HT products for LT greenhouse management are not currently available. In view of the above, the authors initiated a programme partly supported by the Greek Ministries of Education and Agriculture for the development of HT software that is applicable to the LT Mediterranean greenhouse industry. In this paper an expert system (ES) for the diagnosis and treatment of the pests, diseases and nutrient disorders of the aforementioned vegetable species is presented. The ES has been developed on a PC-based shell and will be distributed to extension services and individual farmers for a nominal charge, which is independent of the cost of development. For use in other regions of the Mediterranean, the system is accompanied by a new language translation module which allows a non-specialist user (e.g. extension officer) to translate the knowledge base to the native language or dialect of the local farmers. The particular novelty of the ES is that it is a HT product that has been specially designed for use in a LT situation. The ES is cheap and, apart from a PC does not demand expensive hardware. It is thus readily applicable to the LT greenhouses of the Mediterranean area where low production costs are of paramount importance. Moreover, because of the similarity of cultivation conditions within the Mediterranean basin as a whole, the language translation module extends the application of the product to the significant vegetable production industry of southern Europe and northern Africa.

GEDAS: an integrated geographical expert database system

Abstract In this paper an integrated geographic expert database system is presented which takes advantage of the relational database methodology combined with a geographic information system (GIS) and an expert system (ES). The GIS illustrates the data that are stored in the database after collaboration with the embedded ES. The system is fully implemented and applied to an interesting problem in apiculture.

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.

Reasoning under uncertainty for plant disease diagnosis

The present work describes an operational knowledge-based system able to reason with uncertain knowledge, by using methodologies and formalisms that provide for representation of facts and rules with various degrees of certainty and precision. The user interface is windows based, and its design allows high flexibility both in describing the facts in the knowledge base and in adapting the reasoning mechanism. It can therefore be used to evaluate user-generated hypotheses on plant disorders and diagnostic scenarios, as well as provide an environment for education and training in phytopathology.

A Decision Support System for forest fire management

Forest fires are considered natural phenomena but the magnitude of the problem can be attributed to poor forest management and to the extreme weather conditions. Furthermore, the abolishment of traditional activities related to forests has sent away people from the forests that they used to protect them. The aforementioned reasons result in the annual destruction of large forest areas, agricultural cultivations, industries, animals and even human lives. At the same time, catastrophic floods entail the gradual desolation of the affected areas and large amounts of carbon dioxide along with smoke particles aggravate air quality.In the present paper, a Decision Support System is proposed capable to support policy makers and services to counteract wildfires destruction danger in lowland Pine forests. The system is composed of two major components: (a) A Wildfire Destruction Danger Index useful for preventive and suppressive measures planning and decision policy making and (b) a Forest Management Planning Decision Support System useful for fire risk reduction through forest management plan. The open architecture of the system allows incorporation of data coming from external sources e.g. satellite systems, meteorological stations etc. All its subsystems can stand alone so as to satisfy the needs of responsible organisations (peripheral institutions of fire brigade, forest inspection and local authorities). The proposed system can be both used as an intergraded operational tool in forest fire management and as a training tool for personnel of various services involved.