Predicting stock prices is an interesting field in DataMining. There are many variables affecting stock prices. Especially in this covid19 era which impacts in economy, the stock prices become unpredictable. Telecommunications companies are observed in this research as it is one of the sectors that's still very much in demand in this pandemic situation. Fundamental data will be used to predict the Indonesian telecommunications stock price. Regression techniques will be used as the proposed model. The correlation coefficient shows that despite the covid19 era, fundamental data still play a role in stock market price. Decision Tree Regression produced competitive results compared to other methods.
Computer vision has the challenge to detect the facial emotions of humans. Recently, in computer vision and machine learning, it’s possible to detect emotion from video or image accurate. In our research will propose to classify facial emotion using Haar-Cascade Classifier and Convolutional Neural Networks. The experiment uses the FER2013 dataset which was collected for the facial expression recognition dataset, and we proposed seven classified facial expression. The CNN model gain MSE and accuracy value based on epoch variety. The results showed that with the increase in the epoch value, the smaller MSE value would be obtained, likewise, the accuracy value would be increased. Thus, the proposed algorithm of CNN is proven to be effective for facial emotion detection.
Angkotin is a system that provides an alternative for urban transport to not only be used for passenger transportation, but also as freight service. Therefore, it needs a decision support system for taking order to delivery to the destination according to each criterion from urban transportation. The method used to develop this decision support system is a rule-based system. The result of this research is a decision support system that can help public transportation to find orders that can be taken based on four factors, such as distance, direction, route code, and status of storage capacity. Based on these four factors, the system can provide an order recommendation under the appropriate conditions through the Angkotin application. Based on our experiment, our system performs on 7 seven cases as expected.
Nowadays, educational data can be learned not only for those in Education but also in Information Technology. This happened because education and technology can no longer be separated. Senior high school graduates will take College Entrance Examination to be admitted to public institutions in Indonesia. Sometimes, they share their progress, target, and complain on social media. In this research, we collected data from Twitter. We explore the data to determine student's preparation using Exploratory Data Analysis. The results are positive words in both English and Indonesia, word count, word cloud, and geographical data plot.
Purpose: The research proposed an approach for grouping hospital inpatient service efficiency that have the same characteristics into certain clusters based on BOR, BTO, TOI, and AvLOS indicators using Agglomerative Hierarchical Clustering.Design/methodology/approach: Applying Agglomerative Hierarchical Clustering with dissimilarity measures such as single linkage, complete linkage, average linkage, and ward linkage.Findings/result: The experiment result has shown that ward linkage was given a quite good score of silhouette coefficient reached 0.4454 for the evaluation of cluster quality. The cluster formed using ward linkage was more proportional than the other dissimilarity measures. Ward linkage has generated cluster 0 consists of 23 members, cluster 1 consists of 34 members, while both of cluster 2 and 3 consists of only 1 member respectively. The experiment reported that each cluster had problems with inpatient indicators that were not ideal and even exceeded the ideal limit, but cluster 0 generated the ideal BOR and TOI parameters, both reached 52.17% (12 of 23 hospital inpatient) and 78.36% (18 of 23 hospital inpatient) respectively.Originality/value/state of the art: Based on previous research, this study provides an alternative to produce more proportional, representative and quality clusters in mapping hospital inpatient service efficiency that have the same characteristics into certain clusters using Agglomerative Hierarchical Clustering Method compared to the K-means Clustering Method which is often trapped in local optima.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.