Intelligent Data Analysis Techniques Research Articles

Optimization study of intelligent decision-making system for coal processing plant based on big data analysis

Abstract Optimizing the intelligent decision-making system of coal processing plants is better to improve the economic efficiency of coal processing plants and realize the high-quality development of coal processing plants. In this paper, an integrated intelligent decision-making platform for a coal processing plant is constructed based on big data technology, and the intelligent data analysis techniques of the platform are optimized by using an improved whale optimization algorithm and BP neural network. Examples analyze the optimized crude coal slurry and flotation systems’ processes, and the economic benefits are analyzed. From the optimization of the crude coal slurry sorting system, the ash content in the 0.25mm particle size region was reduced from 55.37% to 13.12%, and the ash content in the −0.125mm particle size region was reduced from 42.68% to 15.96%. From the flotation system optimization, when the flotation time increases from 120s to 180s, the ash content increases from 16.27% to 17.19%, and then to 240s, the ash content increases to 19.44%. Using the integrated intelligent decision-making platform can achieve a net increase in revenue of 4,276,800 yuan for the crude coal slurry sorting system and a net increase of 11,274,200 yuan for the flotation system. This shows that the integrated intelligent decision-making platform can improve the coal processing plant’s quality and efficiency and promote intelligent production.

Main challenges (generation and returned energy) in a deep intelligent analysis technique for renewable energy applications.

In recent years, there has been an increasing demand for Renewable Energy (RE), which refers to energy generated from natural sources such as solar and wind power. Consequently, numerous scientific studies have been conducted to explore various approaches for controlling this type of energy. This work aims to highlight the main challenges associated with the generation and return of RE by employing intelligent data analysis techniques, specifically deep learning. These challenges are examined from different perspectives, including pre-processing, the methodology and techniques used in deep learning, and the evaluation measures employed. Some of the research in this area is focused on predicting the highest amount of energy that can be generated at a particular time and location, while others aim to predict the largest amount of electrical energy that can be returned to the electricity grid to optimize the use of surplus RE resources and maximize their benefits. These efforts are crucial to ensure the effective and continuous operation of the electrical grid. However, despite the efficiency and high accuracy of these models, they are hindered by complex calculations that require considerable time to produce the desired outcomes. Additionally, numerous measures are employed to evaluate the models' performance, including assessing their completion rate, quality of performance, accuracy of results, efficiency, error rate, feasibility of investing in RE, and the largest amount of surplus energy that can be returned to the electricity generation network.

Codon-mRNA prediction using deep optimal neurocomputing technique (DLSTM-DSN-WOA) and multivariate analysis

Based on the principle that the upgrading of any nation begins by raising the level of performance of its institutions that serve the community, including the Ministry of Healthcare and given the development in the field of technology, and the growing need to save the life of persons from different types of diseuses and determined the proteins that increase or prevent any diseuses, so it is found that the world has tended in recent years to intelligent data analysis techniques spatially deep neurocomputing in healthcare fields to predict high quality results in short time. The paper presents model to Codon-mRNA Prediction using Deep Optimal Neurocomputing Technique (DLSTM-DSN-WOA) and Multivariate Analysis. That model consists of five basic stages: The first stage is the process of collecting and preparing the data to make it in suitable form for the decision-making stage and included several steps, including the processing of missing values and condign the target, the second stage involved develop optimization algorithms called Whale Optimization Algorithm (WOA) to build optimal structure to one of the deep neurocomputing network (i.e., long short-term memory (LSTM)). That tool select after deep analysis achieve on optimization algorithms include PSO, BOA, WOA, COA, and FA; this analysis focus on determined for points: the main programming steps, main parameters, advantages, and disadvantages for each algorithm. . The WOA used to find the best structure of deep neurocomputing technique called LSTM that choose to develop after campier among multi techniques (i.e., Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Bi-Directional Long Short-Term Memory (BiLSTM), and AlexNet, GoogleNet). That campier perform based on the programing steps and main parameters affect in each algorithm, because WOA as algorithm having many advantages and characteristics. The proposed model appears as pragmatic intelligent data analysis model for reduce the computation and time of handle huge real data.

Machine Learning Based Diabetes Classification and Prediction for Healthcare Applications.

The remarkable advancements in biotechnology and public healthcare infrastructures have led to a momentous production of critical and sensitive healthcare data. By applying intelligent data analysis techniques, many interesting patterns are identified for the early and onset detection and prevention of several fatal diseases. Diabetes mellitus is an extremely life-threatening disease because it contributes to other lethal diseases, i.e., heart, kidney, and nerve damage. In this paper, a machine learning based approach has been proposed for the classification, early-stage identification, and prediction of diabetes. Furthermore, it also presents an IoT-based hypothetical diabetes monitoring system for a healthy and affected person to monitor his blood glucose (BG) level. For diabetes classification, three different classifiers have been employed, i.e., random forest (RF), multilayer perceptron (MLP), and logistic regression (LR). For predictive analysis, we have employed long short-term memory (LSTM), moving averages (MA), and linear regression (LR). For experimental evaluation, a benchmark PIMA Indian Diabetes dataset is used. During the analysis, it is observed that MLP outperforms other classifiers with 86.08% of accuracy and LSTM improves the significant prediction with 87.26% accuracy of diabetes. Moreover, a comparative analysis of the proposed approach is also performed with existing state-of-the-art techniques, demonstrating the adaptability of the proposed approach in many public healthcare applications.

A study on online travel reviews through intelligent data analysis

The purpose of this paper is to show the application of a set of intelligent data analysis techniques to about 7 million of online travel reviews, with the aim of automatically extracting useful information. The reviews, collected from two popular online tourism-related review platforms, are all those posted by reviewers about one specific Italian location, from 2010 to 2017. To carry out the study, the following methodology is applied: a preliminary statistical analysis is performed to acquire general knowledge about the datasets, such as the geographical distribution of reviewers, their activities, and a comparison among the time of visits and the average scores of the reviews. Then, Natural Language Processing techniques are applied to extract and compare the most frequent words used in the two platforms. Finally, an Association Rule Learning algorithm is applied, to extract preferred destinations for distinct groups of reviewers, by mining interesting associations among the countries of origin of the reviewers and the most frequent destinations visited. By elaborating the available data, it is possible to automatically disclose valuable information for consumers and providers. The information automatically extracted can be exploited, for example, to build a recommender system for customers or a market analysis tool for service providers.

Machine Learning for the Evolutionary Analysis of Breast Cancer

The use of machine learning allows the creation of a predictive data model, as a result of the analysis in a data set with 286 instances and nine attributes belonging to the Institute of Oncology of the University Medical Center. Ljubljana. Based on this situation, the data are preprocessed by applying intelligent data analysis techniques to eliminate missing values as well as the evaluation of each attribute that allows the optimization of results. We used several classification algorithms including J48 trees, random forest, bayes net, naive bayes, decision table, in order to obtain one that given the characteristics of the data, would allow the best classification percentage and therefore a better matrix of confusion, Using 66 % of the data for learning and 33 % for validating the model. Using this model, a predictor with a 71,134 % e effectiveness is obtained to estimate or not the recurrence of breast cancer.

Ground enhancing compound selection using genetic programming

The objective of this paper is to implement genetic programming (GP) methodologies for the modelling and estimation of ground resistance with the use of field measurements related to weather data. Grounding is essential for the safe operation of any electrical installation and protects it against lightning and fault currents. The work utilises both, conventional and intelligent data analysis techniques, for ground resistance modelling. Experimental data consist of field measurements that have been performed in Greece during the previous four years. Five linear regression models have been applied to an appropriately selected dataset, as well as an intelligent approach based on gene expression programming (GEP). The latter combines the advantages of genetic algorithms (GA) and Genetic Programming to avoid the coding explosion problem of GP with the use of simple genetic operations as GA. Every model corresponds to a particular grounding system. A heuristic approach using GEP was performed to produce more robust and general models for grounding estimation. Consequently, a series of larger and more complex GP models were developed to ensure higher accuracy. Results show that evolutionary techniques such as those based on genetic programming are promising for the estimation of the ground resistance.

Reprint of "Updating Markov models to integrate cross-sectional and longitudinal studies".

Clinical trials are typically conducted over a population within a defined time period in order to illuminate certain characteristics of a health issue or disease process. Cross-sectional studies provide a snapshot of these disease processes over a large number of people but do not allow us to model the temporal nature of disease, which is essential for modelling detailed prognostic predictions. Longitudinal studies, on the other hand, are used to explore how these processes develop over time in a number of people but can be expensive and time-consuming, and many studies only cover a relatively small window within the disease process. This paper explores the application of intelligent data analysis techniques for building reliable models of disease progression from both cross-sectional and longitudinal studies. The aim is to learn disease 'trajectories' from cross-sectional data by building realistic trajectories from healthy patients to those with advanced disease. We focus on exploring whether we can 'calibrate' models learnt from these trajectories with real longitudinal data using Baum-Welch re-estimation so that the dynamic parameters reflect the true underlying processes more closely. We use Kullback-Leibler distance and Wilcoxon rank metrics to assess how calibration improves the models to better reflect the underlying dynamics.

Updating Markov models to integrate cross-sectional and longitudinal studies.

Clinical trials are typically conducted over a population within a defined time period in order to illuminate certain characteristics of a health issue or disease process. Cross-sectional studies provide a snapshot of these disease processes over a large number of people but do not allow us to model the temporal nature of disease, which is essential for modelling detailed prognostic predictions. Longitudinal studies, on the other hand, are used to explore how these processes develop over time in a number of people but can be expensive and time-consuming, and many studies only cover a relatively small window within the disease process. This paper explores the application of intelligent data analysis techniques for building reliable models of disease progression from both cross-sectional and longitudinal studies. The aim is to learn disease 'trajectories' from cross-sectional data by building realistic trajectories from healthy patients to those with advanced disease. We focus on exploring whether we can 'calibrate' models learnt from these trajectories with real longitudinal data using Baum-Welch re-estimation so that the dynamic parameters reflect the true underlying processes more closely. We use Kullback-Leibler distance and Wilcoxon rank metrics to assess how calibration improves the models to better reflect the underlying dynamics.

Learning human-mobile nearness with multiple sensors data from steady and non-steady spaces

As mobile devices are becoming equipped with modern sensors, so is the opportunity to develop more intelligent applications in the areas of internet of-things IoT and ambient health intelligence using intelligent data analysis techniques. As such, we present the results of our study on recognising nearness of the human body to a mobile device in a three-dimensional space without having any physical contact with the device. The nearness recognition is done by analysing data from several sensors that are available on a mobile device. We show that the human body generates wave patterns that interact with other naturally occurring ambient signals that could be measured by a mobile device, such as, temperature, humidity, magnetic field, acceleration, gravity, and light. This interaction consequentially alters the patterns of the naturally occurring signals in a steady space to form a non-steady space, and thus, exhibits characteristics that could be learned to predict the nearness of the human body to a mobile device with good accuracy.

Learning human-mobile nearness with multiple sensors data from steady and non-steady spaces

As mobile devices are becoming equipped with modern sensors, so is the opportunity to develop more intelligent applications in the areas of internet of-things (IoT) and ambient health intelligence using intelligent data analysis techniques. As such, we present the results of our study on recognising nearness of the human body to a mobile device in a three-dimensional space without having any physical contact with the device. The nearness recognition is done by analysing data from several sensors that are available on a mobile device. We show that the human body generates wave patterns that interact with other naturally occurring ambient signals that could be measured by a mobile device, such as, temperature, humidity, magnetic field, acceleration, gravity, and light. This interaction consequentially alters the patterns of the naturally occurring signals in a steady space to form a non-steady space, and thus, exhibits characteristics that could be learned to predict the nearness of the human body to a mobile device with good accuracy.

Towards Energy Efficiency Smart Buildings Models Based on Intelligent Data Analytics

This work presents how to proceed during the processing of all available data coming from smart buildings to generate models that predict their energy consumption. For this, we propose a methodology that includes the application of different intelligent data analysis techniques and algorithms that have already been applied successfully in related scenarios, and the selection of the best one depending on the value of the selected metric used for the evaluation. This result depends on the specific characteristics of the target building and the available data. Among the techniques applied to a reference building, Bayesian Regularized Neural Networks and Random Forest are selected because they provide the most accurate predictive results.

Penalized ensemble feature selection methods for hidden associations in time series environments case study: equities companies in Saudi Stock Exchange Market

The problem of optimal subset selection from a large number of time series is addressed in this work using machine learning of financial forecasting. This is a persistent problem in stock market that is largely due to the vast amount of daily-basis data points which require sensitive and robust intelligent data analysis techniques for capturing hidden associations between time series features. In this work, we are interested in generalizing the concept of capturing hidden associations between predictors from financial time series data points in the setting of penalized ensemble feature selection techniques. We have shown how recently developed penalized ensemble feature selection methods are capable of revealing hidden and informative dependencies between equity companies that appear in Saudi Stock Exchange Market in different daily time series datasets. The results have shown that our methods outperformed the well-known lasso regularization method particularly for small sample size.

Leveraging additional knowledge to support coherent bicluster discovery in gene expression data

The increasing availability of gene expression data has encouraged the development of purposely-built intelligent data analysis techniques. Grouping genes characterized by similar expression patterns is a widely accepted – and often mandatory – analysis step. Despite the fact that a number of biclustering methods have been developed to discover clusters of genes exhibiting a similar expression profile under a subgroup of experimental conditions, approaches driven by similarity measures based on expression profiles alone may lead to groups that are biologically meaningless. The integration of additional information, such as functional annotations, into biclustering algorithms can instead provide an effective support for identifying meaningful gene associations. In this paper we propose a new biclustering approach called Additional Information Driven Iterative Signature Algorithm, AID-ISA. It supports the extraction of biologically relevant biclusters by leveraging additional knowledge. We show that AID-ISA allows the discovery of coherent biclusters in baker's yeast and human gene expression data sets.

Intelligent Data Analysis to Model and Understand Live Cell Time-lapse Sequences

One important aspect of cellular function, which is at the basis of tissue homeostasis, is the delivery of proteins to their correct destinations. Significant advances in live cell microscopy have allowed tracking of these pathways by following the dynamics of fluorescently labelled proteins in living cells. This paper explores intelligent data analysis techniques to model the dynamic behavior of proteins in living cells as well as to classify different experimental conditions. We use a combination of decision tree classification and hidden Markov models. In particular, we introduce a novel approach to "align" hidden Markov models so that hidden states from different models can be cross-compared. Our models capture the dynamics of two experimental conditions accurately with a stable hidden state for control data and multiple (less stable) states for the experimental data recapitulating the behaviour of particle trajectories within live cell time-lapse data. In addition to having successfully developed an automated framework for the classification of protein transport dynamics from live cell time-lapse data our model allows us to understand the dynamics of a complex trafficking pathway in living cells in culture.

Intelligent Analysis of Acute Bed Overflow in a Tertiary Hospital in Singapore

Hospital beds are a scarce resource and always in need. The beds are often organized by clinical specialties for better patient care. When the Accident & Emergency Department (A&E) admits a patient, there may not be an available bed that matches the requested specialty. The patient may be thus asked to wait at the A&E till a matching bed is available, or assigned a bed from a different specialty, which results in bed overflow. While this allows the patient to have faster access to an inpatient bed and treatment, it creates other problems. For instance, nursing care may be suboptimal and the doctors will need to spend more time to locate the overflow patients. The decision to allocate an overflow bed, or to let the patient wait a bit longer, can be a complicated one. While there can be a policy to guide the bed allocation decision, in reality it depends on clinical calls, current supply and waiting list, projected supply (i.e. planned discharges) and demand. The extent of bed overflow can therefore vary greatly, both in time dimension and across specialties. In this study, we extracted hospital data and used statistical and data mining approaches to identify the patterns behind bed overflow. With this insight, the hospital administration can be better equipped to devise strategies to reduce bed overflow and therefore improve patient care. Computational results show the viability of these intelligent data analysis techniques for understanding and managing the bed overflow problem.

Data mining applications in hydrocarbon exploration

This paper presents a review of the use of intelligent data analysis techniques in Hydrocarbon Exploration. The term "intelligent" is used in its broadest sense. The process of hydrocarbon exploration exploits data which have been collected from different sources. Different dimensions of data are analyzed by using Statistical Analysis, Data Mining, Artificial Neural Networks and Artificial Intelligence. This review is meant not only to describe the evolution of intelligent data analysis techniques used in different phases of hydrocarbon exploration but also signifying the growing use of Data Mining in various application domains; we avoided a general review of Data Mining and other intelligent data analysis techniques in this paper. The volume of general literature might affect the precision of our view regarding the application of these techniques in hydrocarbon exploration. The review reveals the suitability of existing techniques to data collected from diverse sources in addition to the use of analytical techniques for the process of hydrocarbon exploration.

Intelligent data analysis applied to debug complex software systems

The emergent behavior of complex systems, which arises from the interaction of multiple entities, can be difficult to validate, especially when the number of entities or their relationships grows. This validation requires understanding of what happens inside the system. In the case of multi-agent systems, which are complex systems as well, this understanding requires analyzing and interpreting execution traces containing agent specific information, deducing how the entities relate to each other, guessing which acquaintances are being built, and how the total amount of data can be interpreted. The paper introduces some techniques which have been applied in developments made with an agent oriented methodology, INGENIAS, which provides a framework for modeling complex agent oriented systems. These techniques can be regarded as intelligent data analysis techniques, all of which are oriented towards providing simplified representations of the system. These techniques range from raw data visualization to clustering and extraction of association rules.

Missing Data Imputation Techniques

Intelligent data analysis techniques are useful for better exploring real-world data sets. However, the real-world data sets always are accompanied by missing data that is one major factor affecting data quality. At the same time, good intelligent data exploration requires quality data. Fortunately, Missing Data Imputation Techniques (MDITs) can be used to improve data quality. However, no one method MDIT can be used in all conditions, each method has its own context. In this paper, we introduce the MDITs to the KDD and machine learning communities by presenting the basic idea and highlighting the advantages and limitations of each method.

Developing a well-being monitoring system—Modeling and data analysis techniques

This paper describes how complex data analysis algorithms are being employed to develop a new generation of telecare aimed at helping older people remain living more independently in their own homes for longer. The paper begins by explaining why governments throughout the world are encouraging the development and deployment of new telecare solutions-due in the main to a gradual but constant shift in demographics. Details of a new generation of telecare called 'well-being monitoring' being developed in the UK under the DTI (Department of Trade and Industry) NWTM initiative are provided, DTI [1]. The paper describes how the DTI funded 'Care in the Community Centre' led by BT, has developed a concept model to represent an individual's well-being. The paper goes on to provide an in depth explanation of the Intelligent Data Analysis techniques to be used for monitoring changes in well-being.