IJITCS Vol. 12, No. 6, Dec. 2020
Cover page and Table of Contents: PDF (size: 365KB)
The paper proposes an approach to analyze citizens' comments in e-government using topic modeling and clustering algorithms. The main purpose of the proposed approach is to determine what topics are the citizens' commentaries about written in the e-government environment and to improve the quality of e-services. One of the methods used to determine this is topic modeling methods. In the proposed approach, first citizens' comments are clustered and then the topics are extracted from each cluster. Thus, we can determine which topics are discussed by citizens. However, in the usage of clustering and topic modeling methods appear some problems. These problems include the size of the vectors and the collection of semantically related of documents in different clusters. Considering this, the semantic similarity of words is used in the approach to reduce measure. Therefore, we only save one of the words that are semantically similar to each other and throw the others away. So, the size of the vector is reduced. Then the documents are clustered and topics are extracted from each cluster. The proposed method can significantly reduce the size of a large set of documents, save time spent on the analysis of this data, and improve the quality of clustering and LDA algorithm.[...] Read more.
Sentiment analysis is the process of determining the attitude or the emotional state of a text automatically. Many algorithms are proposed for this task including ensemble methods, which have the potential to decrease error rates of the individual base learners considerably. In many machine learning tasks and especially in sentiment analysis, extracting informative features is as important as developing sophisticated classifiers. In this study, a stacked ensemble method is proposed for sentiment analysis, which systematically combines six feature extraction methods and three classifiers. The proposed method obtains cross-validation accuracies of 89.6%, 90.7% and 67.2% on large movie, Turkish movie and SemEval-2017 datasets, respectively, outperforming the other classifiers. The accuracy improvements are shown to be statistically significant at the 99% confidence level by performing a Z-test.[...] Read more.
Semi.-supervised clustering algorithms aim to enhance the performance of clustering using the pairwise constraints. However, selecting these constraints randomly or improperly can minimize the performance of clustering in certain situations and with different applications. In this paper, we select the most informative constraints to improve semi-supervised clustering algorithms. We present an active selection of constraints, including active must.-link (AML) and active cannot.-link (ACL) constraints. Based on Radial-Bases Function, we compute lower-bound and upper-bound between data points to select the constraints that improve the performance. We test the proposed algorithm with the base-line methods and show that our proposed active pairwise constraints outperform other algorithms.[...] Read more.
Malaria is life threatening disease in Ethiopia specifically in Tigray region. Having common symptoms with other diseases makes it complex and challenging to diagnose effectively. In this paper case based reasoning framework for malaria diagnosis has been designed to diminish the challenges faced by inexperienced practitioners during malaria diagnosis and to solve the problem on shortage of health professionals. The required knowledge for this study was collected through interview and document analysis from domain experts, malaria patient history cards and other related relevant documents. In the case acquisition process the manual format of cases makes the process too challenging. Decision tree is used to model the acquired knowledge. The case structure was then constructed using the selected most determinant attributes. Machine learning approach is applied to select the most relevant features. Feature-vector case representation technique is applied to represent the collected malaria cases. Jcolibri programming tool integrated with Eclipse and Nearest Neighbor retrieval algorithm are used to design the framework. To the end based on the results we can say that the machine learning approach can be used to select most relevant attributes in diseases having several common symptoms and designing case-based diagnosis frameworks could overcome the main problems observed in health centers of Tigray. As an artifact the framework is evaluated by statistical analysis, comparative evaluation, user evaluation and other evaluation techniques. Averagely 79 % precision, 89 % recall, 91.4% accuracy and 78.8% domain expert’s evaluation was the results scored.[...] Read more.
In the healthcare industry, the Internet of Medical Services (IOMT) plays a vital role throughout the increasing performance, reliability, and efficiency of an electronic device. Healthcare is also characterized as being complicated due to its highly diverse and large number of shareholders. Data diversity refers to the continuum of various types of elements in the data. The integration of data is difficult where different sources can adopt different identification for the same entity, but there is no explicit connection. Researches are contributing to a digitized Health care system through interconnections available medical resources and health care services. This Research presents the contribution of IoT to people in the field of Healthcare, highlighting the issues in different data integration, analysis of the existing algorithms and models, applications, and future challenges of IoT in terms of healthcare medical services. Big data analytics that incorporates millions of fragmented, organized, and unstructured sources of data will play a key role in how health care will be delivered in the future.[...] Read more.