This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.
The Rose Expert System is basically gives the information regarding the diseases, viruses and their symptoms and chemical controls which are used to prevent the diseases and viruses of cultivation of Rose.
This Rose Expert Advisory System is simulation of more than one expert. This system is developed in Java Server Pages. There are two modules "Information system" and "Advisory system" are embedded in present system. For advising the farmers in the disease identification and preventive measures of Rose plantation, this "Rose Expert Advisory System" uses backward chaining mechanism for building Rule Based Expert system which results in giving exact disease. If rule base system fails in giving the exact disease then Rose Expert Advisory System provides an alternative system using Machine Learning Techniques - Optimization Algorithm, which produces subset of diseases with probabilistic values. Then the system uses Particle Swarm Optimization Algorithm for each disease by taking some sign values from the user and gives a nearest disease to the user with the preventive measures.
Expert Advisory System - Information System -
Rule Based-Optimization Algorithms- Particle Swarm Optimization Algorithm - Web Based - JSP - SQL
Expert system can be defined as a tool for information generation from knowledge. Information is either found in various forms or generated from data and/or knowledge. Text, images, video, audio are forms of media on which information can be found, and the role of information technology is to invent, and devise tools to store and retrieve this information. Statistical information is a good example of information generated from data while advises generated by an expert system is a good example of information generated from knowledge.
Roses are symbol of beauty, fragrance and are used to convey the message of love. In India roses are grown for cut flowers, making essential oil, rose water and gulkand. Dry petals of roses are also used for making incense sticks. Roses are native of Himalayas regions, Asia, China, Japan, Europe and North America. There are about 150 species but very few species have played a major role in evolving modern roses. These species are Rosa gallica, R. damascene
1.1 Rose Varieties
Red and dark red: Black Velvet, Crimson Glory, Happiness
Orange: Hawaii, Super, Star, Duke of Windsor
Yellow: Summer Sunshine, Golden Giant, Kiss of Fire, Double Delight
Pink: Eiffel Tower, First Love, First Prize
White: Virgo, White Christmas,
Bicolor: Suspense (red and yellow), Perfecta (pink and white),
Lavender: Blue, Africa Star, Paradise
Novel Color: Careless Love
Rose can be grown successfully in variable climatic zones. However, moderate temperature, bright sunshine and high light intensity are good for flower production. It is suggested that the quality rose blooms are obtained during December to April, with approximately 5 to 6 blooms per plant each in 60 cm. and above, and 45 to 59 cm. category stem length. Roses do well in soils having pH upto 6.0 to 7.5 but it can also grow satisfactorily in alkaline soil with pH upto 8.4. Rose can be successfully cultivated in mild climate with good sunshine. It ceases to grow at vary low temperature
The growing temperature markedly influences the growth and flowering of rose plants. Seasonal variation in temperature has a pronounced effect on flowering, flower quality and longevity of field grown roses. A minimum temperature of 7.9 degree centigrade and maximum of 22.6 degree centigrade with 6 sunshine hours during winter season has been found to delay flower bud opening, improve flower quality and longevity in rose cultivar while 12.7 degree centigrade and, 27.8 degree centigrade minimum and maximum temperature respectively in spring season with 6 sunshine hours has been found to induce early flower bud opening and reduce the longevity of intact flowers considerably without affecting the quality of flowers as compared to winter seasons. The rise in temperature during summer and rain seasons adversely affects flower quality and longevity while inducing earliest flower bud opening.
Rose plants grow well in good fertile soil. They can, however, be grown in all types of soil with proper drainage facilities. Well-drained medium loamy soil having adequate organic matter is ideal. The best soil reaction for roses should be in the pH range of 6.0 to 6.5. They will do reasonably well at a pH of 7.0 and slightly higher, but some nutritional problems may be encountered from time to time. A pH less than 6 is usually too low. A soil, which has been in cultivation and has a depth of at least 45 cm. is good for rose growing. The subsoil must have the capacity to retain sufficient moisture, bet at the same time permit good drainage. Adverse soil conditions, however, affect growth and flowering to a great extent. Budded pants have lesser tolerance to adverse conditions than unbudded rootstocks. Roses fall into the sensitive category of pants with respect to salinity and solidity tolerance.
Pick an area that has parlous of great flagging stain. Towering spot has a PH aligned station the amount of tart moment the blacken is at about 5. 5 - 7. 0.
Whole-length matter agnate manure or lime helps to aid the roots of your roses. You should soak the roots leverage drool or puddle clay for numerous memoir, and cut winterkill slab root ' s ends that are disastrous.
The basic 3 - 4 weeks succeeding planting your roses, you should imbue them generally. Generally this is when the top 2 inches of stain is dry. Roses requirement a lot of hydration and chop to stay on healthy.
2. PROPOSED SYSTEM:
The proposed system is Rose expert advisory system. It is divided into two aspects
In Information system, the user can get all the static information about different species, Diseases, Symptoms, chemical controls, Preventions, Pests, Virus of Rose flower and plants.
In Advisory System, the user is having an interaction with the expert system online; the user has to answer the questions asked by the Expert System. Depends on the response by the user the expert system decides the disease and displays its control measure of disease.
It is aimed at a collaborative venture with eminent Agriculture Scientist and Experts in the area of Rose Plantation with an excellent team of computer Engineers, programmers and designers.
This web application is expected to have the following features:
This web application provides time- to- time updates of Rose information to the users at their door steps regarding diseases, virus and its control measure which leads to good yields.
This site contains four major sections named Information Systems of Rose, Rose Advisory System, other services related to web application and an additional feature is links to other agriculture systems
The web directory service, articles and the discussion forum service provided in the website will help the floriculture fraternity in a greater way to interact each other to produce better findings in the area of floriculture field.
2.1. Functional Requirements for Rose Expert System:
The system needs the information about the symptoms from the user to produce the output.
The outputs of the system will be:
Information Diseases & Viruses
Small Description about the disease & Viruses
Chemical controls & Nutrients
The information collected through experts is stored as a database (Knowledge Base) that serves as a repository for quick processing and future retrieval. The system stores the following information in terms of html files.
About Rose system
About Rose Varieties
Climate and Soil
The System Stores the information related to Expert System in knowledge base in the following ways.
2.1.4.Rules A set of rules that constitute the program stored in a rule memory of production memory and on an inference engine using JSP files required to execute the rules.
2.1.5.Dataset: The data in the MySQL database can be used as any other data stored in a database. This greatly increases the opportunity with which you can conduct post-analysis of the monitoring data.
3. MACHINE LEARNING
ARCHITECTURE OF ROSE
CROP ADVISORY EXPERT SYSTEM
Fig 1. Rose Crop Advisory System
Fig.2 Architecture of subsystem -I
(RULE BASED SYSTEM)
Fig 3. Architecture of subsystem -II (Optimization Algorithm):
Fig.4 Architecture of subsystem -III
(Particle Swarm Optimization Algorithm)
3.1. RULE BASED SYSTEM
In the Rule Based System the System takes the Symptoms as Input and produce the Exact Disease with all the facts and Rules that matches with in the Knowledge base. This Rule Based System Consists of Knowledge Base, Inference Engine, User Interface, Expert and the User.
Collect the rules whose conditions match facts in Working Memory.
If more than one rule matches
Use conflict resolution strategy to eliminate all but one
Do actions indicated by the rules
(Add facts to Working Memory or delete facts from Working Memory)
Until problem is solved or no condition match
The output of the this system produce the exact disease basing on the symptoms produced by the user which leads to a disadvantage that if any of the symptom does not match with the knowledge it will not produce any output for the further proceedings.
If the system1 (Rule Based System) unable to produce the exact disease then the system2 starts performing its work.
Optimization Algorithm: -
Optimization (Computation Vector, Memory Matrix, Resultant vector)
Computation Vector is the input vector that has to be mapped with the Memory Matrix and produce the result in the Resultant vector.
Computation Vector is an Input Boolean string of length n. and Memory Matrix is generated from the Knowledge base with all Boolean value of order m X n.
Step 1: Read the Computation vector as Boolean String of n length.
Step 2: Create a Resultant vector that initialize to null and counter to zero
Step 3: Construct the Memory Matrix of Boolean Value from the Knowledgebase.
Step 4: for i in 0 to m in the Memory Matrix of m X n
Make counter as zero. (Perform Step 4a and step 4b m times)
Step 4a: for j in 0 to n element in the row
Compare the jth element of the Computation vector with the jth element of the row
if both the element are equal
counter++ (increment the counter ).
Step 4b: Assign the ith element of the Resultant vector with the counter.
Step 5: (The resultant vector will be within the value of count which is has to be converted into
probability value of percentage value).
Step 6: For each element in the Resultant Vector replace the value by value/m*100 for Percentage
value of replace the value by value/m*1 by Probability value.
Step 7: End the process
Particle Swarm Optimization Algorithm:
For each particle
Â Initialize particle with feasible random number
Â For each particle
Â Calculate the fitness value
Â Â Â Â Â Â Â If the fitness value is better than the best fitness value (pbest) in history
Â Â Â Â Â Â Â Â Â Â Â Set current value as the new pbest
Â Â Â End
Choose the particle with the best fitness value of all the particles as the gbest
Â Â Â For each particle
Â Â Â Â Â Â Â Calculate particle velocity according to velocity update equation
Â Â Â Â Â Â Â Update particle position according to position update equation
Â Â Â End
While maximum iterations or minimum error criteria is not attained.
RESULTS & REPORTS
4.1 Rule Based System Screen Shots:
4.2. Optimization Algorithm Screen shots:
4.3. Particle Swarm Optimization Screen Shots:
5. FUTURE WORK
In Rose Expert System we have impletemented three algorithms to identify the Diseases and viruses of the rose plant and also give the advices to the farmer about the prevention of that particular disease. Those algorithms are
Rule based Algorithm
Particle Swarm Optimiation
In future we want to enhance the system in such a way the it has to perform multi language (Translators ) , animations , video's for the userinterface design of the system and markerting statistics in the system.
Research issues in agricultural expert systems are categorized under these topics: integration of software components with agricultural expert systems, knowledge sharing and reuse, intelligent retrieval of agricultural data, and automatic knowledge acquisition. The future trends in research and development of agricultural expert systems are expected to be using agent based approaches to solve the integration problem of different software components, developing domain specific tasks that will contribute to knowledge sharing and reuse and automatic knowledge acquisition.
The project "Rose Expert Advisory System" is a web-enabled application developed using java server pages (jsp) and MySql database is used as backend. So as to ensure the quality of the software, all software engineering concepts, including test cases are implemented.
Its main emphasis is to have a well designed interface for giving advices and suggestions in the area of horticulture (Rose) field by providing facilities like dynamic interaction between expert system and the user without the need of expert at all times.
By the thorough interaction with the users and beneficiaries the functionality of the System can be extended further to many more areas in and around the world.
Thank you to every one