Data Mining - Concepts and Techniques.

International Joint Conference on Neural Networks

The discovery and development of novel materials in the field of energy are essential to accelerate the transition to a low-carbon economy. Bringing recent technological innovations in automation, robotics and computer science together with current approaches in chemistry, materials synthesis and characterization will act as a catalyst for revolutionizing traditional research and development in both industry and academia. This Perspective provides a vision for an integrated artificial intelligence approach towards autonomous materials discovery, which, in our opinion, will emerge within the next 5 to 10 years. The approach we discuss requires the integration of the following tools, which have already seen substantial development to date: high-throughput virtual screening, automated synthesis planning, automated laboratories and machine learning algorithms. In addition to reducing the time to deployment of new materials by an order of magnitude, this integrated approach is expected to lower the cost associated with the initial discovery. Thus, the price of the final products (for example, solar panels, batteries and electric vehicles) will also decrease. This in turn will enable industries and governments to meet more ambitious targets in terms of reducing greenhouse gas emissions at a faster pace. The discovery and development of advanced materials are imperative for the clean energy sector. We envision that a closed-loop approach, which combines high-throughput computation, artificial intelligence and advanced robotics, will sizeably reduce the time to deployment and the costs associated with materials development.

/pdf/accelerating-the-discovery-of-materials-for-clean-energy-in-2ejogam5fn.pdf

Accelerating the discovery of materials for clean energy in the era of smart automation

Wisdom of Crowds: The Value of Stock Opinions Transmitted through Social Media

Abstract Class imbalance is often a problem in various real-world data sets, where one class (i.e. the minority class) contains a small number of data points and the other (i.e. the majority class) contains a large number of data points. It is notably difficult to develop an effective model using current data mining and machine learning algorithms without considering data preprocessing to balance the imbalanced data sets. Random undersampling and oversampling have been used in numerous studies to ensure that the different classes contain the same number of data points. A classifier ensemble (i.e. a structure containing several classifiers) can be trained on several different balanced data sets for later classification purposes. In this paper, we introduce two undersampling strategies in which a clustering technique is used during the data preprocessing step. Specifically, the number of clusters in the majority class is set to be equal to the number of data points in the minority class. The first strategy uses the cluster centers to represent the majority class, whereas the second strategy uses the nearest neighbors of the cluster centers. A further study was conducted to examine the effect on performance of the addition or deletion of 5 to 10 cluster centers in the majority class. The experimental results obtained using 44 small-scale and 2 large-scale data sets revealed that the clustering-based undersampling approach with the second strategy outperformed five state-of-the-art approaches. Specifically, this approach combined with a single multilayer perceptron classifier and C4.5 decision tree classifier ensembles delivered optimal performance over both small- and large-scale data sets.

分群式取樣法於類別不平衡問題之研究;Clustering-Based Under-sampling in Class Imbalanced Data

Nowadays, large amount of data is available everywhere. Therefore, it is very important to analyze this data in order to extract some useful information and to develop an algorithm based on this analysis. This can be achieved through data mining and machine learning. Machine learning is an integral part of artificial intelligence, which is used to design algorithms based on the data trends and historical relationships between data. Machine learning is used in various fields such as bioinformatics, intrusion detection, Information retrieval, game playing, marketing, malware detection, image deconvolution and so on. This paper presents the work done by various authors in the field of machine learning in various application areas.

Machine learning and its applications: A review

International Diabetes Federation (IDF) stated that 382 million people are living with diabetes worldwide. Over the last few years, the impact of diabetes has been increased drastically, which makes it a global threat. At present, Diabetes has steadily been listed in the top position as a major cause of death. The number of affected people will reach up to 629 million i.e. 48% increase by 2045. However, diabetes is largely preventable and can be avoided by making lifestyle changes. These changes can also lower the chances of developing heart disease and cancer. So, there is a dire need for a prognosis tool that can help the doctors with early detection of the disease and hence can recommend the lifestyle changes required to stop the progression of the deadly disease. Diabetes if untreated may turn into fatal and directly or indirectly invites lot of other diseases such as heart attack, heart failure, brain stroke and many more. Therefore, early detection of diabetes is very significant so that timely action can be taken and the progression of the disease may be prevented to avoid further complications. Healthcare organizations accumulate huge amount of data including Electronic health records, images, omics data, and text but gaining knowledge and insight into the data remains a key challenge. The latest advances in Machine learning technologies can be applied for obtaining hidden patterns, which may diagnose diabetes at an early phase. This research paper presents a methodology for diabetes prediction using a diverse machine learning algorithm using the PIMA dataset. The accuracy achieved by functional classifiers Artificial Neural Network (ANN), Naive Bayes (NB), Decision Tree (DT) and Deep Learning (DL) lies within the range of 90–98%. Among the four of them, DL provides the best results for diabetes onset with an accuracy rate of 98.07% on the PIMA dataset. Hence, this proposed system provides an effective prognostic tool for healthcare officials. The results obtained can be used to develop a novel automatic prognosis tool that can be helpful in early detection of the disease. The outcome of the study confirms that DL provides the best results with the most promising extracted features. DL achieves the accuracy of 98.07% which can be used for further development of the automatic prognosis tool. The accuracy of the DL approach can further be enhanced by including the omics data for prediction of the onset of the disease.

Deep learning approach for diabetes prediction using PIMA Indian dataset

Due to the rapid growth in IT technology, digital data have increased availability, creating novel security threats that need immediate attention. An intrusion detection system (IDS) is the most promising solution for preventing malicious intrusions and tracing suspicious network behavioral patterns. Machine learning (ML) methods are widely used in IDS. Due to a limited training dataset, an ML-based IDS generates a higher false detection ratio and encounters data imbalance issues. To deal with the data-imbalance issue, this research develops an efficient hybrid network-based IDS model (HNIDS), which is utilized using the enhanced genetic algorithm and particle swarm optimization(EGA-PSO) and improved random forest (IRF) methods. In the initial phase, the proposed HNIDS utilizes hybrid EGA-PSO methods to enhance the minor data samples and thus produce a balanced data set to learn the sample attributes of small samples more accurately. In the proposed HNIDS, a PSO method improves the vector. GA is enhanced by adding a multi-objective function, which selects the best features and achieves improved fitness outcomes to explore the essential features and helps minimize dimensions, enhance the true positive rate (TPR), and lower the false positive rate (FPR). In the next phase, an IRF eliminates the less significant attributes, incorporates a list of decision trees across each iterative process, supervises the classifier’s performance, and prevents overfitting issues. The performance of the proposed method and existing ML methods are tested using the benchmark datasets NSL-KDD. The experimental findings demonstrated that the proposed HNIDS method achieves an accuracy of 98.979% on BCC and 88.149% on MCC for the NSL-KDD dataset, which is far better than the other ML methods i.e., SVM, RF, LR, NB, LDA, and CART.

/pdf/a-hybrid-intrusion-detection-model-using-ega-pso-and-2o0l7hzf.pdf

A Hybrid Intrusion Detection Model Using EGA-PSO and Improved Random Forest Method

In an effort to provide a more efficient representation of the speech signal, the application of the wavelet analysis is considered. This research presents an effective and robust method for extracting features for speech processing. Based on the time‐frequency multi‐resolution property of wavelet transform, the input speech signal is decomposed into various frequency channels. The major issues concerning the design of this Wavelet based speech recognition system are choosing optimal wavelets for speech signals, decomposition level in the DWT, selecting the feature vectors from the wavelet coefficients. More specifically automatic classification of various speech signals using the DWT is described and compared using different wavelets. Finally, wavelet based feature extraction system and its performance on an isolated word recognition problem are investigated. For the classification of the words, three layered feed forward network is used. General Terms

/pdf/speech-recognition-by-wavelet-analysis-gie8fnyvcc.pdf

Speech Recognition by Wavelet Analysis

Purpose




The purpose of this paper is to develop a prediction model to study the factors affecting the academic performance of students pursuing an undergraduate professional course (BCA). For this purpose, the ensemble model of decision tree, gradient boost algorithm and Naive Bayes techniques is created to achieve best and accurate results. Monitoring the academic performance of students has emerged as an essential field as it plays a vital role in the accurate development and growth of students’ critical and cognitive thinking. If the academic performance of students during the initial years of the graduation can be predicted, different stakeholders, i.e. government, policymakers, academicians, can be helped to make significant remedial strategies. This comprehensible practice can go a long way in shaping the ideologies of young minds, enhancing pedagogical practices and reframing of curriculum. This study aims to develop positive steps that can be taken to enhance future endeavours in the field of education.




Design/methodology/approach




A questionnaire was prepared specifically to find out influential factors affecting the academic performance of the students. Its specific area of investigation was demographic, social, academic and behavioural factors that influence the performance of the students. Then, an ensemble model was built using three techniques based on accuracy rate. A 10-fold cross-validation technique was applied to access the fitness of results obtained from proposed ensemble model.




Findings




The result obtained from ensemble model provides efficient and accurate prediction of student performance and helps identify the students that are at risk of failing or being a drop-out. The effect of previous semester’s academic performance shows a significant impact on current academic performance along with other factors (such as number of siblings and distance of university from residence). Any major mishap during past one year also affects the academic performance along with habit-based behavioural factors such as consumption of alcohol and tobacco.




Research limitations/implications




Though the existing model considers aspects related to a student’s family income and academic indicators, it tends to ignore major factors such as influence of peer pressure, self-study habits and time devoted to study after college hours. An attempt is made in this paper to examine the above cited factors in predicting the academic performance of the students. The need of the hour is to develop innovative models to assess and make advancements in the present educational set-up. The ensemble model is best suited to study all factors needed to accomplish a robust and reliable model.




Originality\value




The present model is developed using classification and regression algorithms. The model is able to achieve 99 per cent accuracy with the existing data set and is able to identify the influential factors affecting the academic performance. As early detection of at-risk students is possible with the proposed model, preventive and corrective measures can be proposed for improving the overall academic performance of the students.

Sachin Ahuja

Papers

Machine learning and its applications: A review

Deep learning approach for diabetes prediction using PIMA Indian dataset

A Hybrid Intrusion Detection Model Using EGA-PSO and Improved Random Forest Method

Speech Recognition by Wavelet Analysis

An ensemble-based model for prediction of academic performance of students in undergrad professional course