Includes bibliographical references.

Article 1. Filtering Infrequent Behavior in Business Process Discovery by Using the Minimum Expectation -- Article 2. Comparisons of Speech Parameterisation Techniques for Classification of Intellectual Disability Using Machine Learning -- Article 3. Enhanced Bootstrapping Algorithm for Automatic Annotation of Tweets -- Article 4. Exploiting Visual Features in Financial Time Series Prediction -- Article 5. MCDM Approach for Mitigation of Flooding Risks in Odisha (India) Based on Information Retrieval -- Article 6. Data Analytic Techniques for Developing Decision Support System on Agrometeorological Parameters for Farmers -- Article 7. Predictive Analytical Model for Microblogging Data Using Asset Bubble Modelling.

[Article Title: Filtering Infrequent Behavior in Business Process Discovery by Using the Minimum Expectation / Ying Huang, Liyun Zhong, and Yan Chen, p.1-15]

Abstract: The aim of process discovery is to discover process models from the process execution data stored in event logs. In the era of “Big Data,” one of the key challenges is to analyze the large amounts of collected data in meaningful and scalable ways. Most process discovery algorithms assume that all the data in an event log fully comply with the process execution specification, and the process event logs are no exception. However, real event logs contain large amounts of noise and data from irrelevant infrequent behavior. The infrequent behavior or noise has a negative influence on the process discovery procedure. This article presents a technique to remove infrequent behavior from event logs by calculating the minimum expectation of the process event log. The method was evaluated in detail, and the results showed that its application in existing process discovery algorithms significantly improves the quality of the discovered process models and that it scales well to large datasets.

https://doi.org/10.4018/IJCINI.2020040101

[Article Title: Comparisons of Speech Parameterisation Techniques for Classification of Intellectual Disability Using Machine Learning / Gaurav Aggarwal and Latika Singhm, p. 16-34]

Abstract: Classification of intellectually disabled children through manual assessment of speech at an early age is inconsistent, subjective, time-consuming and prone to error. This study attempts to classify the children with intellectual disabilities using two speech feature extraction techniques: Linear Predictive Coding (LPC) based cepstral parameters, and Mel-frequency cepstral coefficients (MFCC). Four different classification models: k-nearest neighbour (k-NN), support vector machine (SVM), linear discriminant analysis (LDA) and radial basis function neural network (RBFNN) are employed for classification purposes. 48 speech samples of each group are taken for analysis, from subjects with a similar age and socio-economic background. The effect of the different frame length with the number of filterbanks in the MFCC and different frame length with the order in the LPC is also examined for better accuracy. The experimental outcomes show that the projected technique can be used to help speech pathologists in estimating intellectual disability at early ages.

https://doi.org/10.4018/IJCINI.2020040102

[Article Title: Enhanced Bootstrapping Algorithm for Automatic Annotation of Tweets / Mudasir Mohd, Rafiya Jan, and Nida Hakak, p. 35-60]

Abstract: Annotations are critical in various text mining tasks such as opinion mining, sentiment analysis, word sense disambiguation. Supervised learning algorithms start with the training of the classifier and require manually annotated datasets. However, manual annotations are often subjective, biased, onerous, and burdensome to develop; therefore, there is a need for automatic annotation. Automatic annotators automatically annotate the data for creating the training set for the supervised classifier, but lack subjectivity and ignore semantics of underlying textual structures. The objective of this research is to develop scalable and semantically rich automatic annotation system while incorporating domain dependent characteristics of the annotation process. The authors devised an enhanced bootstrapping algorithm for the automatic annotation of Tweets and employed distributional semantic models (LSA and Word2Vec) to augment the novel Bootstrapping algorithm and tested the proposed algorithm on the 12,000 crowd-sourced annotated Tweets and achieved a 68.56% accuracy which is higher than the baseline accuracy.

https://doi.org/10.4018/IJCINI.2020040103

[Article Title: Exploiting Visual Features in Financial Time Series Prediction / Adil Gürsel Karaçor and Turan Erman Erkan, p. 61-76]

Abstract: The possibility to enhance prediction accuracy for foreign exchange rates was investigated in two ways: first applying an outside the box approach to modeling price graphs by exploiting their visual properties, and secondly employing the most efficient methods to detect patterns to classify the direction of movement. The approach that exploits the visual properties of price graphs which make use of density regions along with high and low values describing the shape; hence, the authors propose the name ‘Finance Vision.' The data used in the predictive model consists of 1-hour past price values of 4 different currency pairs, between 2003 and 2016. Prediction performances of state-of-the-art methods; Extreme Gradient Boosting, Artificial Neural Network and Support Vector Machines are compared over the same data with the same sets of features. Results show that density based visual features contribute considerably to prediction performance.

https://doi.org/10.4018/IJCINI.2020040104

[Article Title: MCDM Approach for Mitigation of Flooding Risks in Odisha (India) Based on Information Retrieval / Debesh Mishra and Suchismita Satapathy, p. 77-91]

Abstract: Multi-criteria decision-making (MCDM) provides a suitable platform for groups as well as promotion of the participants' role in decision processes. This also enables the development of real participatory processes essential for the successful implementation and sustainable flood management programs. The present study contributes by applying two MCDM approaches for weighting the criteria related to the environmental impacts of flooding. Moreover, an attempt was made in this study by an extensive review of literature, and consultations with experts to identify the environmental impacts of flooding in Odisha State (India). Then, the Best Worst Method (BWM) followed by the Step-Wise Weight Assessment Ratio Analysis (SWARA) method was used to rank the environmental impacts which were considered as the risk factors. The result of this study will be useful to the governance system for an effective and proper planning, and implementation of flood mitigation projects.

https://doi.org/10.4018/IJCINI.2020040105

[Article Title: Data Analytic Techniques for Developing Decision Support System on Agrometeorological Parameters for Farmers / Sowmya B.J., Krishna Chaitanya S., S. Seema, and K.G. Srinivasa, p.92-107]

Abstract: The day-to-day lives of humans are changing remarkably due to the evolution in tools, techniques and technology across the planet. This evolution is not only impacting the growth of humans but also contributing to the growth and well-being of society and country. The domain of data analytics (DA) and internet of things (IoT) is very much facilitating this growth. But there have been only a handful of innovations and explorations in the field of agriculture, although it being the backbone and largely contributing to the gross domestic product (GDP) of a country like India. The reason for it may be profuse, such as the erratic weather conditions, improper irrigation, farmers being skeptical using modern tools and many more. But being in a developing country that has its primary focus on invention and innovation, a consensus has to be reached so that the modern tools and technologies, abet agriculture throughout the country. In our work, an attempt is made to analyze the different aspects that influences the variable outcomes in agriculture with the aid of various data analytic algorithms. Rainfall, humidity and temperature are some of the variables that determine the type of crop. Therefore, the task of prediction of crop type given these factors using decision trees and support vector machines (SVM) is implemented, and the accuracy of the models are computed. Here, more focus is given to the state of Karnataka and to its major crops. With rice, ragi and maize being some of the predominant crops, an analysis is portrayed considering the yield across the state.

https://doi.org/10.4018/IJCINI.2020040106

[Article Title: Predictive Analytical Model for Microblogging Data Using Asset Bubble Modelling / Srinidhi Hiriyannaiah, Siddesh G.M., and Srinivasa K.G., p. 108-118]

Abstract: In recent days, social media plays a significant role in the ecosystem of the big data world and its different types of information. There is an emerging need for collection, monitoring, analyzing, and visualizing the different information from various social media platforms in different domains like businesses, public administration, and others. Social media acts as the representative with numerous microblogs for analytics. Predictive analytics of such microblogs provides insights into various aspects of the real-world entities. In this article, a predictive model is proposed using the tweets generated on Twitter social media. The proposed model calculates the potential of a topic in the tweets for the prediction purposes. The experiments were conducted on tweets of the regional election in India and the results are better than the existing systems. In the future, the model can be extended for analysis of information diffusion in heterogeneous systems.

https://doi.org/10.4018/IJCINI.2020040107