Intelligent Data Mining Technique Research Articles

Stock Market Prediction Using Machine Learning Techniques

The stock market is a very important activity in the finance business. Its demand is consistently growing. Stock market prediction is the process of determining the future value of company stock or other financial instruments traded on a financial exchange. For some decades Artificial Neural Network (ANN), which is one intelligent data mining technique has been used for Stock Price Prediction. It has been trusted as the most accurate consideration. This paper surveys different machine learning models for stock price prediction. We have trained the available stockdataofAmericanAirlinesforthisproject.Th eprogramminglanguagethatwe have used in this paper is Python. The Machine Learning (ML) models used in this project are Decision Tree (DT), Support Vector Regression (SVR), Random Forest (RF),and ANN. The datahereissplitinto70%fortrainingand30%fort esting.The dataset contains stock data for the last 5 years. From the simulation results, it is shown that Random Forest performs better as compared to others. Thus, it can be used in the real-time implementation. Keywords Machine Learning, Stock Price, Prediction, American Airlines, Support Vector Machine (SVR), Artificial Neural Network (ANN), Random Forest (RF), Decision Tree (DT).

Insulation aging and fault diagnosis of high-voltage equipment based on deep Q-networks

In response to the escalating demand for electric energy in the world, the maintenance technology for electric power equipment has evolved significantly. This study addresses the critical issue of insulation aging in high voltage equipment through an innovative approach. By integrating advanced Deep Q-networks (DQN) algorithms and intelligent data mining techniques, our proposed diagnostic scheme enables accurate and timely fault detection. The intelligent DQN algorithms process real-time equipment data, providing essential insights into operational status and faults. Implementing this research offers a strategic framework for enhancing the reliability of high-voltage equipment, contributing to stable system operation, and laying the groundwork for future advancements in equipment condition maintenance.

The Data Mining Based Model for Detection of Fraudulent Behavior in Water Consumption

Abstract: There are many significant problems facing by water supplying companies and agencies because of fraudulent water consumption. Which is resulting a higher loss of income to water supplying agencies. Finding efficient measurements for detecting fraudulent activities has beenan active research area in recent years. To detect this fraudulent behaviour faced by water companies’ intelligent datamining techniques can be used to reduce the loss. This research explores the use of two classification techniques SVM and KNN to detect suspicious fraud water customers. The SVM based approach uses customer load profile attributes to expose abnormal behaviour that is known to be correlated with non-technical loss activities. The data has been collected from the historical data of the company billing system. The accuracy of the generated model obtained 74% which is better than the current manual prediction procedures.The system will help the company to predict suspicious water customers.

Intelligent Application to Detect Heart Disease Issues and Treatment

Intelligent Application to Detect Heart Disease Issues and Treatment. It might have happened so many times that you or someone yours need doctors help immediately, but they are not available due to some reason. Intelligent application for detection heart rate disease is an end user support provide an online/offline consultation. Here, we propose an application that allows users to get instant guidance on their heart disease through an intelligent system. The application is fed with various details and the heart disease associated with those details. The application allows user to share their heart related issues. It then processes user specific details to check for various illness that could be associated with it. Here we use some intelligent data mining techniques to guess the most accurate illness that could be associated with patient’s details. Based on result, the can contact doctor accordingly for further treatment. The system allows user to view doctor’s details too. The system can be used for free heart disease consulting online or offline.

The Analysis of Public Opinion in Colleges and Universities Oriented to Wireless Networks under the Application of Intelligent Data Mining

In recent years, the incidence of public opinion in colleges and universities has been high. Monitoring, forecasting, and responding to public opinion of students in colleges and universities have increasingly become the work that education management departments at all levels attach great importance to. For each university, how to understand the sensation of teachers and students in real time in the era of informationization entering the intelligent campus has become an urgent problem. How to collect college campus network information, analyze and manage this information, and find hot topics from it has a profound impact on the reform of colleges and universities. Hence, in this paper, we propose a public opinion analysis framework based on intelligent data mining technique. Its advantage lies in the fact that it can withdraw the needed and unknown knowledge and regularities from the massive network data and host log data. It is a new attempt to use data mining in achieving public opinion. At present, data mining algorithm applied to public opinion analysis mainly has four basic patterns: association, sequence, classification, and clustering. Data mining technology is advanced for: it can process large amount of data. It does not need the users’ subjective evaluation and is more likely to discover the ignored and hidden information. Here, initially, the dataset is collected, which is preprocessed and divided into a training set and test set. Feature extraction of the text is done using Linear Discriminant Analysis (LDA). After that, text cosine similarity calculation is performed to compute the similarity between text vectors obtained from the LDA. Convolutional neural network (CNN) is used for classification purpose. We proposed Krill Herd Harmony Search Optimization Algorithm (KHHSOA) for optimizing the CNN and classifying the text into positive and negative opinion. The proposed system is simulated using MATLAB simulation tool, and the performance is analyzed in terms of metrics like accuracy, precision, recall, F -measure, kappa coefficient, and error rate. The proposed method is proved to be better when compared with the existing techniques.

Disease Prediction using Naïve Bayes - Machine Learning Algorithm

It can occur on many occasions that you or a loved one requires urgent medical assistance, but they are unavailable due to unforeseen circumstances, or that we are unable to locate the appropriate doctor for the care. As a result, we will try to incorporate an online intelligent Smart Healthcare System in this project to solve this issue. It's a web-based programmed that allows patients to get immediate advice about their health problems. The aim of the smart healthcare system is to create a web application that can take a user's symptoms and predict diseases, as well as serve as an online consultant for various diseases. We created an expert system called Smart Health Care System, which is used to make doctors' jobs easier. A machine examines a patient at a basic level and recommends diseases that may be present. It begins by inquiring about the patient's symptoms; if the device is able to determine the relevant condition, it then recommends a doctor in the patient's immediate vicinity. The system will show the result based on the available accumulated data. We're going to use some clever data mining techniques here. We use several intelligent data mining techniques to guess the most accurate illness that could be associated with a patient's symptoms, and we use an algorithm (Naive Bayes) to map the symptoms with potential diseases based on a database of many patients' medical records. This system not only makes doctors' jobs easier, but it also benefits patients by getting them the care they need as soon as possible. Keywords: Disease Prediction, Naïve Bayes, Machine Learning Algorithm, Smart Healthcare System.

Heart disease prediction using Advanced Machine Learning Algorithms

It might have happened so many times that you or someone yours need doctors help immediately, but they are not available due to some reason. The Heart Disease Prediction application is an end user support to the online. Here, we propose a web application that allows users to get instant guidance on their heart disease through an intelligent system online. The application is fed with various details and the heart disease associated with those details. The applications allows user to share their heart related issues. It then processes user specific details to check for various illnesses that could be associated with it. Here we use some intelligent data mining techniques to the most accurate that could be associated with patient‟s details. Based on result, system automatically shows the result specific doctors for further treatment and the system allows user to view doctor‟s details.

Prediction Analysis for Business To Business (B2B) Sales of Telecommunication Services using Machine Learning Techniques

Sales prediction analysis requires intelligent data mining techniques with accurate prediction models and high reliability. In most cases, business highly relies on information as well as demand forecast of the sales trends. This research uses B2B sales data for analysis. The B2B data could provide information on how telecommunication company should manage its sales team, products, and budgeting flows. The accurate estimates enable Telecommunication company to survive the market war and increase with market growth. Comprehensible predictive models were studied and analyzed using a technique of machine learning to improve the prediction of the future sale. It is hard to cope with big data and sale prediction accuracy if the system of traditional forecast is used. In this study, machine learning technique was also used to analyze the reliability of B2B sales. In addition, at the end of this research, other measures and techniques used to predict sales were introduced. The predictive model with best performance evaluation is recommended to forecast the trending B2B sales. The study results are put into an order of reliability and accuracy of the best method to predict and forecast including estimation, evaluation, and transformation. The best performance model found was Gradient Boost Algorithm. The result form graph the data close together from beginning till end of data target MSE and MAPE result are the best result than other method, MSE =24.743.000.000,00 and MAPE =0,18. This model performed maximum accuracy in predicting and forecasting of the future B2B sales.

The efficiency of soft sensors modelling in advanced control systems in oil refinery through the application of hybrid intelligent data mining techniques

Quality variables cannot be automatically measured to all nor be measured at a high cost, infrequently, nor with high delays, such as laboratory analysis and online analyser. Therefore, data-driven soft sensors are inferential models which use online available sensors, such as temperature, pressure, and flow rate among others, to predict the quality variables. Soft sensors which are built using historical data of the processes are normally developed from the supervisory control and data acquisition (SCADA) systems connected with PLC or DCS (distribution control systems) as the daily reports on the oil refinery processes. These systems are then obtained from laboratory observation/measurements. Notably, the main issue in the development of the soft sensor is the treatment of missing data, outlier detection, selection of input variables, model training, validation, and soft sensor maintenance to adopt the heavy-duty oil refineries to improve the products of the crude oil and increase yield. In this article, the improvement in the virtual sensor based on hybrid soft computing methods (FLS and NN), which are combined into ANFIS, will be employed to construct the soft sensor model. Moreover, RST will be used to reduce the fuzzy rules and discretisation method to optimise and deal with the large continuous data. It was found from the implementation of rough set theory and discretisation methods that these two methods solved the complexity and nonlinearity of the soft sensor model. This model was employed for the refining process measurements data of the oil refinery from two different crude oil sources, in which the database of the measurements and processes was combined to improve the quality of data and discover the knowledge stored in the data pattern. It was indicated from this study result that the ANFIS model is able to manage the complex data to predict two important parameters of light naphtha (API and RVP) compared to the simple regression model. Additionally, controlling and monitoring the process are crucial actions performed to achieve the 4th industrial revolution and IoT. This study has contributed to the assistance in breaking the barriers of privacy between oil industries and the applicability of soft sensors modelling in the changes of data sources to achieve remarkable data analysis. The analyses result of RVP show the efficiency of ANFIS compare with linear regression regarding the generalization and overfitting.

Seismic response and design of buried concrete pipes subjected to soil loads

Concrete pipes are a crucial element in sustaining contemporary life because they afford appropriate means to transport drinking water, sewage, and storm water. Thus, these useful assets must be designed correctly. The current methodology to design these assets is based on factors called the bedding factors; these factors have been developed considering only static loads. Evidences from previous studies showed that buried structures, including concrete pipes, are vulnerable to failure due to seismic shake. However, no study has been found in the literature to address the response and the design of buried concrete pipes subjected to seismic shake. Thus, this research aims to study the seismic response and seismic design of underground concrete pipe subjected to soil loads. The combined influence of the seismic shake and diameter of pipe, burial depth, installation condition, and intensity of the seismic shake have been studied using a carefully developed finite element model. The results showed that the seismic shake noticeably rises the maximum bending moment; however, the percentage increase remarkably influenced by the diameter of the pipe and the burial depth. Furthermore, the percentage rise of the maximum bending moment declines as the installation quality becomes poorer. The results also showed that the maximum bending moment rises nonlinearly as the acceleration rises. Comparisons with the current AASHTO bedding factors illustrated that these factors either conservative or unsafe. The reasons for these inaccuracies in the current design bedding factors have been discussed and novel equations to predict bedding factors that consider the seismic shake have been derived using novel intelligent data mining technique. The accuracy of the proposed equations has been demonstrated and thus, these equations can be used by practitioners/designers to implicate the effect of seismic shake in the design of buried concrete pipes.

NSE Stock Market Prediction Using Deep-Learning Models

The neural network, one of the intelligent data mining technique that has been used by researchers in various areas for the past 10 years. Prediction and analysis of stock market data have got an important role in today’s economy. The various algorithms used for forecasting can be categorized into linear (AR, MA, ARIMA, ARMA) and non-linear models (ARCH, GARCH, Neural Network). In this paper, we are using four types of deep learning architectures i.e Multilayer Perceptron (MLP), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) for predicting the stock price of a company based on the historical prices available. Here we are using day-wise closing price of two different stock markets, National Stock Exchange (NSE) of India and New York Stock Exchange (NYSE). The network was trained with the stock price of a single company from NSE and predicted for five different companies from both NSE and NYSE. It has been observed that CNN is outperforming the other models. The network was able to predict for NYSE even though it was trained with NSE data. This was possible because both the stock markets share some common inner dynamics. The results obtained were com- pared with ARIMA model and it has been observed that the neural networks are outperforming the existing linear model (ARIMA).

Combination of cognitive and HCI modeling for the design of KDD-based DSS used in dynamic situations

Recent work in dynamic decision support systems (DSS) has taken impressive steps toward data preparation and storage, intelligent data mining techniques, and interactive visualization. However, it remains difficult to deal with the uncertainty and complexity generated by the Knowledge Discovery in Databases (KDD). This paper launches the challenge by introducing cognitive modeling for specifying decision-maker behaviors more naturally and intuitively. It consists in introducing cognitive modeling for dynamic situations involving visual KDD-based dynamic DSS. This research work presents an adaptation of a well-known cognitive model under the KDD specificities. We provide cognitive modeling application in visual KDD-based dynamic DSS for the fight against nosocomial infections in an intensive care unit. Finally, we built a series of evaluations verifying the system's utility and usability.

Machine Learning–Based Differential Network Analysis: A Study of Stress-Responsive Transcriptomes in Arabidopsis

Machine learning (ML) is an intelligent data mining technique that builds a prediction model based on the learning of prior knowledge to recognize patterns in large-scale data sets. We present an ML-based methodology for transcriptome analysis via comparison of gene coexpression networks, implemented as an R package called machine learning-based differential network analysis (mlDNA) and apply this method to reanalyze a set of abiotic stress expression data in Arabidopsis thaliana. The mlDNA first used a ML-based filtering process to remove nonexpressed, constitutively expressed, or non-stress-responsive "noninformative" genes prior to network construction, through learning the patterns of 32 expression characteristics of known stress-related genes. The retained "informative" genes were subsequently analyzed by ML-based network comparison to predict candidate stress-related genes showing expression and network differences between control and stress networks, based on 33 network topological characteristics. Comparative evaluation of the network-centric and gene-centric analytic methods showed that mlDNA substantially outperformed traditional statistical testing-based differential expression analysis at identifying stress-related genes, with markedly improved prediction accuracy. To experimentally validate the mlDNA predictions, we selected 89 candidates out of the 1784 predicted salt stress-related genes with available SALK T-DNA mutagenesis lines for phenotypic screening and identified two previously unreported genes, mutants of which showed salt-sensitive phenotypes.

Special Issue on International Organized Sessions of JSAI2012

Perhaps the above themes reflect part of the current interests in AI (in Japan). Two sessions have the same theme —data mining. For the age of “big data,” more intelligent data mining techniques will be required. Of course the same or similar problems have been pointed out and discussed before the age. Thus, we are still on the way of researching for the intelligent and effective data mining. In addition, more intelligent treatment of data from the Web will be necessary. Thus, a session on web intelligence was organized. The second session discussed challenges in AI. Since 2012 was the celebrating (100th birthday) year of Alan Turing, under the big name, they discussed fundamental problems and challenges in AI. From authors in these sessions, some interesting papers have been submitted. After peer reviews, the following papers have been accepted.

AKNOBAS: A knowledge-based segmentation recommender system based on intelligent data mining techniques

Recommender Systems have recently undergone an unwavering improvement in terms of efficiency and pervasiveness. They have become a source of competitive advantage in many companies which thrive on them as the technological core of their business model. In recent years, we have made substantial progress in those Recommender Systems outperforming the accuracy and added-value of their predecessors, by using cutting-edge techniques such as Data Mining and Segmentation. In this paper, we present AKNOBAS, a Knowledge-based Segmentation Recommender System, which follows that trend using Intelligent Clustering Techniques for Information Systems. The contribution of this Recommender System has been validated through a business scenario implementation proof-of-concept and provides a clear breakthrough of marshaling information through AI techniques.

An intelligent information infrastructure to support knowledge discovery

The lack of seamless data interchange and efficient data analysis hinders the formation of an effective information infrastructure that serves as the universal platform for data interchange across heterogeneous database systems. This paper proposes the design and implementation of an information infrastructure embracing the emerging eXtensible Markup Language (XML) open standard, together with an intelligent data mining technique combining On-Line Analysis Process (OLAP) and rule-based reasoning approaches to support knowledge discovery. To validate the feasibility of this hybrid approach, an information infrastructure prototype is developed and tested in a company with description of this case example covered in this paper.

An intelligent online machine fault diagnosis system

Traditional help desk service relies heavily on the expertise of service personnel. This article describes an intelligent data mining technique that combines neural network and rule-based reasoning with case-based reasoning to mine information from the customer service database for online machine fault diagnosis. This technique has been implemented into a help-desk system that supports online machine fault diagnosis over the Internet.