Data Mining - Concepts and Techniques.

Data Mining Practical Machine Learning Tools and Techniques

Thank you for reading database systems a practical approach to design implementation and management. As you may know, people have search hundreds times for their chosen readings like this database systems a practical approach to design implementation and management, but end up in malicious downloads. Rather than enjoying a good book with a cup of coffee in the afternoon, instead they juggled with some harmful virus inside their laptop.

Database Systems A Practical Approach To Design Implementation And Management

Water quality monitoring is an important component of water resources management. In order to predict two water quality variables, namely dissolved oxygen (DO; mg/L) and chlorophyll-a (Chl-a; µg/L) in the Small Prespa Lake in Greece, two standalone deep learning (DL) models, the long short-term memory (LSTM) and convolutional neural network (CNN) models, along with their hybrid, the CNN–LSTM model, were developed. The main novelty of this study was to build a coupled CNN–LSTM model to predict water quality variables. Two traditional machine learning models, support-vector regression (SVR) and decision tree (DT), were also developed to compare with the DL models. Time series of the physicochemical water quality variables, specifically pH, oxidation–reduction potential (ORP; mV), water temperature (°C), electrical conductivity (EC; µS/cm), DO and Chl-a, were obtained using a sensor at 15-min intervals from June 1, 2012 to May 31, 2013 for model development. Lag times of up to one (t − 1) and two (t − 2) for input variables pH, ORP, water temperature, and EC were used to predict DO and Chl-a concentrations, respectively. Each model’s performance in both training and testing phases was assessed using statistical metrics including the correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE), their normalized equivalents (RRMSE, RMAE; %), percentage of bias (PBIAS), Nash–Sutcliffe coefficient ($$E_{NS}$$), Willmott’s Index, and graphical plots (Taylor diagram, box plot and spider diagram). Results showed that LSTM outperformed the CNN model for DO prediction, but the standalone DL models yielded similar performances for Chl-a prediction. Generally, the hybrid CNN–LSTM models outperformed the standalone models (LSTM, CNN, SVR and DT models) in predicting both DO and Chl-a. By integrating the LSTM and CNN models, the hybrid model successfully captured both the low and high levels of the water quality variables, particularly for the DO concentrations.

Short-term water quality variable prediction using a hybrid CNN–LSTM deep learning model

The ability to predict student performance in a course or program creates opportunities to improve educational outcomes. With effective performance prediction approaches, instructors can allocate resources and instruction more accurately. Research in this area seeks to identify features that can be used to make predictions, to identify algorithms that can improve predictions, and to quantify aspects of student performance. Moreover, research in predicting student performance seeks to determine interrelated features and to identify the underlying reasons why certain features work better than others. This working group report presents a systematic literature review of work in the area of predicting student performance. Our analysis shows a clearly increasing amount of research in this area, as well as an increasing variety of techniques used. At the same time, the review uncovered a number of issues with research quality that drives a need for the community to provide more detailed reporting of methods and results and to increase efforts to validate and replicate work.

https://dl.acm.org/doi/pdf/10.1145/3293881.3295783

Predicting academic performance: a systematic literature review

The major intention of higher education institutions is to supply quality education to its students. One approach to get maximum level of quality in higher education system is by discovering knowledge for prediction regarding the internal assessment and end semester examination. The projected work intends to approach this objective by taking the advantage of fuzzy inference technique to classify student scores data according to the level of their performance. In this paper, student’s performance is evaluated using fuzzy association rule mining that describes Prediction of performance of the students at the end of the semester, on the basis of previous database like Attendance, Midsem Marks, Previous semester marks and Previous Academic Records were collected from the student’s previous database, to identify those students which needed individual attention to decrease fail ration and taking suitable action for the next semester examination.

/pdf/fuzzy-association-rule-mining-based-model-to-predict-2ewdjwvas1.pdf

Fuzzy Association Rule Mining based Model to Predict Students’ Performance

Forecasting share performance becomes more challenging issue due to the enormous amount of valuable trading data stored in the stock database. Currently, existing forecasting methods are insufficient to analyze the share performance accurately. There are two main reasons for that: First, the study of existing forecasting methods is still insufficient to identify the most suitable methods for share price prediction. Second, the lack of investigations made on the factors affecting the share performance. In this regard, this study presents a systematic review of the last fifteen years on various machine learning techniques in order to analyze share performance accurately. The only objective of this study is to provide an overview of the machine learning techniques that have been used to forecast share performance. This paper also highlights a how the prediction algorithms can be used to identify the most important variables in a share market dataset. Finally, we could have succeeded to analyze share performance effectively. It could bring benefits and impacts to researchers, society, brokers and financial analysts. Full Text: PDF DOI: http://dx.doi.org/10.11591/ijece.v6i6.13323

/pdf/performance-forecasting-of-share-market-using-machine-o08cpib82o.pdf

Performance Forecasting of Share Market using Machine Learning Techniques: A Review

This paper presents a Classification data model using decision tree for the purpose of analyzing water quality data of MAA Narmada River at Harda district. The data model was implemented in WEKA software.  Classification using decision tree was applied to classify /predict the pollutant class of water. It is observed in the analysis that the Nitrogen (NH3_N ,NO3_N), pH ,Temp _C, BOD, COD, other parameter relevant to water processes play an important role to assess the quality of river water. In this experiment we have used five attribute of water quality data which can affect accuracy of water.

https://www.arjournals.org/index.php/bjdmn/article/download/1563/764

Decision tree approach to build a model for water quality

In modern context, integrated approach of science and technology has given new subjects such as bioinformatics. This discipline of informatics gave a pathway to understand the larger data of various biological systems in much simplified manner. The various attributes studied in the form of computational patterns result in phylogenetic tree construction. These phylogenetic trees establish both similarities and dissimilarities among organisms. Different algorithms of clustering were studied and compared on various parameters to establish the best among them and utilities of others methods as well. The current text makes us informative about clustering methods used to generate phylogenetic trees by both distance- and character-based analyses.

Review of Clustering Methods: Toward Phylogenetic Tree Constructions

In these days, stock market forecasting is one of the most interesting issues, which has gained a more attention due to vast profits. To precisely predict the price of share and making profits has been always challenging task since the longest period of time. This has engrossed the interest and attention of stock brokers, economists and applied researchers. Traditional methods like Fundamental analysis, Technical analysis, and Regression methods are not suitable for this task because these tools and techniques are based on totally different analytical approaches and requiring highly expertise and justification in the area. In this sequence, Association Rule Mining is one of the most interesting research areas for finding the associations, correlations among items in a database. It can discover all useful patterns from stock market dataset. The aim of this research study is to help stock brokers, investors so that they can earn maximum profits for each trading.

/pdf/an-association-rule-mining-model-for-finding-the-interesting-3x1h5elvqd.pdf

Shailesh Jaloree

Papers

Fuzzy Association Rule Mining based Model to Predict Students’ Performance

Performance Forecasting of Share Market using Machine Learning Techniques: A Review

Decision tree approach to build a model for water quality

Review of Clustering Methods: Toward Phylogenetic Tree Constructions

An Association Rule Mining Model for Finding the Interesting Patterns in Stock Market Dataset