Data mining with agricultural soil databases is a relatively young research area. In agricultural field, the determination of soil category mainly depends on the atmospheric conditions and different soil characteristics. Classification as an essential data mining technique used to develop models describing different soil classes. Such analysis can present us with a complete understanding of various soil databases at large. In our study, we proposed a novel Neuro-fuzzy classification based technique and applied it to large soil databases to find out significant relationships. We used our technique to three benchmark data sets from the UCI machine learning repository for soil categorization and they were namely Statlog (Landsat Satellite), Covertype, and 3 data sets. Our objective was to develop an efficient classification model with the proposed method and, therefore compare its performance with two well-known supervised classification algorithms Multilayer Perceptron and Support Vector Machine. We estimated the performance of these classification techniques in terms of different evaluation measures like Accuracy, Kappa statistic, True-Positive Rate, False-Positive Rate, Precision, Recall, and F-Measure. The proposed technique had an accuracy of 99.4 % with the Statlog data set, 97.7 % with the Covertype data set and 90 % with the 3 data set; and in every aspect, it performed better than Multilayer Perceptron and Support Vector Machine algorithms.
Data mining consists of extracting interesting patterns representing knowledge from real-world databases. The software applications related with data mining includes various methodologies developed by both commercial and research organizations. Different data mining techniques used to...
... middle of paper ...
...It combines the human alike logical reasoning of fuzzy based systems with the learning and connectedness structure of ANNs by means of the fuzzy sets and linguistic model based approaches. In our work, we proposed a novel Neuro-fuzzy based classification method for soil data mining. We applied our method to three benchmark data sets from the UCI machine learning repository for soil classification and, therefore compare its performance with MLP and SVM based classification models.
This research study is arranged as follows: Section 2 includes the related works done in this field; Section 3 describes our proposed Neuro-fuzzy classification based method. Section 4 explains the methodology in terms of our proposed neuro-fuzzy method, MLP, and SVM. Section 5 discusses the classification performance analysis and results; and the Section 6 is reserved for the conclusion.
Stephen V. Stehman, “Selecting and interpreting measures of thematic classification accuracy”. Remote Sensing of Environment, Vol. 62, No.1, pp.77–89, 1997.
Traditional business intelligence tools are being replaced by data discovery software. The data discovery software has numerous capabilities that are dominating purchase requirements for larger distribution. A challenge remaining is the ability to meet the dual demands of enterprise IT and business users.
Stergiou, C., & Siganos, D. (2011, August 6). Neural Networks. Retrieved August 6, 2011, from
Data mining has emerged as an important method to discover useful information, hidden patterns or rules from different types of datasets. Association rule mining is one of the dominating data mining technologies. Association rule mining is a process for finding associations or relations between data items or attributes in large datasets. Association rule is one of the most popular techniques and an important research issue in the area of data mining and knowledge discovery for many different purposes such as data analysis, decision support, patterns or correlations discovery on different types of datasets. Association rule mining has been proven to be a successful technique for extracting useful information from large datasets. Various algorithms or models were developed many of which have been applied in various application domains that include telecommunication networks, market analysis, risk management, inventory control and many others
An important field in computer science today is artificial intelligence. The novel approaches that computer scientists use in this field are looked to for answers to many of the problems that have not been solved through traditional approaches to software engineering thus far. One of the concepts studied and implemented for a variety of tasks in artificial intelligence today is neural networks; they have proven successful in offering an approach to some problems in the field, but they also have some failings.
Since the 1980's there have been renewed research efforts dedicated to neural networks. The present interest is largely due to the difficult problems confronted by artificial intelligence, and due to the deeper understanding of how the brain works, the recent developments in theoretical models, technologies and algorithms. One motivation of neural network research is the desire to build a new breed of powerful computers to solve a variety of problems that have proved to be very difficult with conventional computers. Another motivation is the desire to develop cognitive models that can serve as an alternative way to artificial intelligence. Human brain functions have not yet been successfully simulated in an AI system. Some existing neural network, on the other hand, have shown potential for these abilities. Using self-organization capabilities, neural networks are able to acquire and organize knowledge through learning in response to external stimuli. This paper addresses many techniques used in neural networks and possible applications in artificial intelligence. Some generic information about hybrid intelligent systems is also provided.
The fuzzy is basic set of rules which is based on system error and change in error which expert advice into automatic control condition for self adaptive controller. Fuzzy represents a sequence of control mechanism to adjust the effect of certain system stimulations. It reflects the expert conditions in to appropriate control design.
The dynamics of our society bring many challenges and opportunities to the business world. Within the last decade, hundreds of jobs have emerged particularly in the technology sector to help keep up with the ever-changing world and to compete on a larger and better scale than the competition. Two key job markets and the basis of this research paper are business intelligence or BI and data mining or DM. These two fields play a very important role in small to large companies and are becoming higher desired sectors within the back offices of the workplace. This paper will explore what the meaning of BI and DM really is, how they are used and what we can expect as workers and learners of the technology and business fields for the future.
The texture refers to the structure of the soil in relation to small, medium or large particles in a specific soil mass (Ball 2001). Soil texture is classified based on the amount of sand, silt and clay present in a soil sample (Schoonover & Crim 2015). A coarse soil is a sand or loamy soil, a medium soil is a loam, silt loam or silt whereas a fine soil is a sandy clay, silty clay or just clay (Ball 2001). The particles of the clay are very small which means they have a large surface area (What is Soil Texture? 2017). Due to the surface area, the water gets stuck well to the clay and its ability to retain moisture gets high (What is Soil Texture? 2017). If the surface area is high, more area is available for positively charged plant nutrients
HAND, D. J., MANNILA, H., & SMYTH, P. (2001).Principles of data mining. Cambridge, Mass, MIT Press.
... applied on different Domain data sets and sub level data sets. The data sets are applied on Maximum entropy, Support Vector Machine Method, Multinomial naïve bayes algorithms, I got 60-70% of accuracy. The above is also applied for the Unigrams of Maximum entropy, Support Vector Machine Method, Multinomial naïve bayes algorithms achieved an accuracy of 65-75%. Applied the same data on proposed lexicon Based Semantic Orientation Analysis Algorithm, we received better accuracy of 85%. In subjective Feature Relation Networks Chi-square model using n-grams, POS tagging by applying linguistic rules performed with highest accuracy of 80% to 93% significantly better than traditional naïve bayes with unigram model. The after applying proposed model on different sets the results are validated with test data and proved our methods are more accurate than the other methods.
There has also been lot of research in building systems that can monitor and investigate soil fertility and nutrition levels. Soil fertility data with dynamic, spatial and temporal characteristics of soil are fed to the systems which then use data mining techniques to come to analyze and diagnose soil problems. Such information can be very critical for success of crop.
Sammut, S. (N/A). A Soil Information System for the Maltese Islands. Available: http://www.wise-rtd.info/sites/default/files/d-2008-05-26-Project_presentation.pdf. Last accessed 29th Dec 2013.
Machine learning systems can be categorized according to many different criteria. We will discuss three criteria: Classification on the basis of the underlying learning strategies used, Classification on the basis of the representation of knowledge or skill acquired by the learner and Classification in terms of the application domain of the performance system for which knowledge is acquired.