The proper use of information technology can improve the efficiency and effectiveness of an organization’s performance. The use of information technology in educational institutions also require good governance so as to ensure transparency, efficiency, and effectiveness of any business process that runs on the institutions. Audit is one of the ways that can be done to determine the company’s ability to execute business process in it so that the performance of the process in the company can run better and more effective, and it can also improve the performance of employees. The audit process conducted at Office X aims to evaluate the work program using the COBIT 5 framework as a guide because it already contains four main perspectives, namely the customer perspective, financial perspective, internal business process perspective, and the learning and growth perspective. Results of research conducted at Office X show that the capability level of the four processes in the audit which are APO07 (Manage human resources), BAI02 (Manage requirements definition), BAI04 (Manage availability and capacity), and EDM04 (Ensure resource optimization) achieved by the Office still stop at level 1 and there is still a difference of 4 levels from what is expected by the company so that there needs to be improvements to achieve the specified target level 5.

The heart is the most important part of the human body. Any abnormality in heart results heart related illness in which it obstructs blood vessels which causes heart attack, chest pain or stroke. Care and improvement of the health by the help of identification, prevention, and care of any kind of diseases is the main goal. So for this various prediction analysis methods are used which job is to identify the illness at prelim phase so that prevention and care of heart disease is done. This paper emphasizes on the care of heart diseases at a primitive phase so that it will lead to a successful cure. In this paper, diverse data mining classification method like Decision tree classification, Naive Bayes classification, Support Vector Machine classification, and k-NN classification are used for determination and safeguard of the diseases.

Sentiment analysis is an application of artificial intelligence that determines the sentiment associated sentiment with a piece of text. It provides an easy alternative to a brand or company to receive customers' opinions about its products through user generated contents such as social media posts. Training a machine learning model for sentiment analysis requires the availability of resources such as labeled corpora and sentiment lexicons. While such resources are easily available for English, it is hard to find them for other languages such as Arabic. The aim of this research is to build an Arabic sentiment lexicon using a corpus-based approach. Sentiment scores were propagated from a small, manually labeled, seed list to other terms in a term co-occurrence graph. To achieve this, we proposed a graph propagation algorithm and compared different similarity measures. The lexicon was evaluated using a manually annotated list of terms. The use of similarity measures depends on the fact that the words that are appearing in the same context will have similar polarity. The main contribution of the work comes from the empirical evaluation of different similarity to assign the best sentiment scores to terms in the co-occurrence graph.

The buying behavior of the consumer is grown nowadays through recommender systems. Though it recommends, still there are limitations to give a recommendation to the users. In order to address data sparsity and scalability, a hybrid approach is developed for the effective recommendation in this paper. It combines the feature engineering attributes and collaborative filtering for prediction. The proposed system implemented using supervised learning algorithms. The results empirically proved that the mean absolute error of prediction was reduced. This approach shows very promising results.

In this paper, we have focused on the data mining technique on market data to establish meaningful relationships or patterns to determine the determinate critical factors of commodity price. The data is taken from Ethiopia commodity exchange and 18141 data sets were used. The dataset contains all main information. The hybrid methodology is followed to explore the application of data mining on the market dataset. Data cleaning and data transformation were used for preprocessing the data. WEKA 3.8.1 data mining tool, classification algorithms are applied as a means to address the research problem. The classification task was made using J48 decision tree classification algorithms, and different experimentations were conducted. The experiments have been done using pruning and unpruning for all attributes. The developed models were evaluated using the standard metrics of accuracy, ROC area. The most effective model to determine the determinate critical factors for the commodity has an accuracy of 88.35% and this result is a good experiment result.
The output of this study is helpful to support decision-making activities in the area of the Ethiopia Commodity Exchange. The study support commodity suppliers to take care of the determinant factors work towards maintaining quality. Ethiopia Commodity Exchange (ECX), as the main facilitator of commodity exchanges, can also use the model for setting price ranges and regulations.

The Internet of Things (IoT) is becoming pervasive and immersive due to the recent advancements in communication and sensing technologies. The proliferation of smart devices and their sensing capabilities has opened new opportunities and business models. The billions of connected sensing devices are generating enormous amount of data. The sensing as a service concept has the potential to provide a wide variety of services to citizens, companies and public administrations. This paper presents a sensing as service vision for IoT in different domains such as agriculture, waste management, supply chain, traffic management and others. Moreover, different applications of sensing as service model is analyzed and discussed in detail. In this paper, we specifically propose a service oriented sensing as service architecture to realize the vision of sensing as a service. The proposed service oriented architecture has the potential to address the challenges of heterogeneity, integration and interoperability of a sensing as service concept and can open new business opportunities.