Telematika
Not a member yet
319 research outputs found
Sort by
Knowledge Management In Instiki E-Learning To Increase Student Learning Satisfaction
Get PDFPurpose: The use of the concept of knowledge management can manage the knowledge of the teacher or lecturer and then it can be conveyed to the studentsDesign/methodology/approach: Knowledge Management SystemFindings/result: The application of the Knowledge Management System at the INSTIKI LMS was able to increase student learning satisfaction. The results of the questionnaire assessment show that student learning satisfaction increases after implementing INSTIKI e-learning, the average value of studentOriginality/value/state of the art: Implementation of Knowledge Management System on INSTIKI campu
Deep-RIC: Plastic Waste Classification using Deep Learning and Resin Identification Codes (RIC)
Get PDFIn this study, the authors designed an algorithm based on deep learning that can automatically classify plastic waste according to Resin Identification Codes (RIC). The proposed algorithm is built through several stages as follows. In the first stage, image acquisition of plastic waste is carried out, which is the input of the designed algorithm. The acquired plastic waste image must display the resin code of the plastic waste to be classified. Furthermore, the acquired image is divided into two sets, namely training and testing sets. The training set contains images of plastic waste used in the training phase of the deep learning architecture DenseNet-121 to identify the resin code of each plastic waste image and classify it into the appropriate class. The training phase is run for 100 epochs, and at each epoch, the cross-entropy loss function is calculated, which expresses the performance of the deep learning architectures in classifying plastic waste images. In the next stage, a trained deep learning architecture is used to classify the plastic waste images from the test set. Classification performance in the test set is also expressed as the cross-entropy loss function value. In addition, the accuracy value has also been calculated, which shows the percentage of the number of plastic waste images successfully classified correctly to the total number of plastic waste images in the test set, which the best accuracy is equal to 85%
Conv-Tire: Tire Condition Assessment using Convolutional Neural Networks
No full textPurpose: In this study, the authors designed an algorithm based on convolutional neural networks that can automatically assess tire quality.Design/methodology/approach: The proposed algorithm is built through several stages as follows. In the first stage, the tire images, which are the input of the designed algorithm, are acquired. Further, the acquired images are divided into two sets, namely training and testing sets. The training set contains tire images used in the training phase of several convolutional neural networks (CNN) architectures such as ResNet-50, MobileNetV2, Inception V3, and DenseNet-121. The training phase is carried out in a number of epochs, and at each epoch, the cross entropy loss function will be calculated which expresses the performance of the CNN architecture in classifying tire images. For this reason, the training stage requires a label or reference that shows the feasibility of the tires displayed in each image.Findings/result: In the testing phase, trained CNN architectures are used to classify tire images from the test set. Classification performance in the test set is also expressed in terms of cross-entropy loss function value. In addition, the accuracy value has also been calculated which shows the percentage of the number of tire images that are successfully classified correctly to the total number of tire images in the test set, namely the DenseNet-121 model has the best accuracy of 92.62%.Originality/value/state of the art: Given the high accuracy achieved by our algorithm, this work can be used as a reference by other researchers, specifically to benchmark their tire quality classification methods developed in the future
Analisys Mortality Rate of Tuberculosis Patients Seen From Age and Length of Treatment at RSUD Dr. M. Haulussy Ambon Using the K-Means Clustering Algorithm for the Rapidminer Application
Get PDFTuberculosis (TB) is an infectious disease that causes major health problems in the world by the bacterium Mycobacterium tuberculosis. It spreads through the air when people with TB cough or sneeze. Maluku was in the 10th position with the most TB cases in Indonesia in 2016. Various programs and activities to control TB in Ambon City are carried out, from the process of finding cases, treating patients, health promotions to sputum examination. After that, an evaluation is carried out as an effort to prevent and control to measure the level of success and effectiveness of institutional programs in order to achieve organizational goals. To find out the development of TB cases in Maluku, especially the city of Ambon, the research conducted this time also used the k-means clustering algorithm for the rapidminer application to analyze the death rate of TB patients in terms of age and length of treatment at RSU Dr. M. Haulussy Ambon. The research conducted obtained that the highest number of patients who died were in cluster 1 with an age range of 36-55 years, then followed by the second position in cluster 0 with an age range of 6-33 years, and the last in cluster 2 with a total number of patients. died in the age range of 59-84 years. The length of stay of patients in the hospital varies from half a day to day 21 and is experienced by patients who recover as well as die. The highest patient mortality rate is in the productive age group, rarely does exercise and often engages in active activities and meets many people every day, smoking habits and lack of knowledge about health are the causes of more productive age groups suffering from T
Augmented Reality Introduction to Animals of the Archipelago to Grow the Nation\u27s Love for Children
Get PDFPurpose: Produce Augmented Reality applications as a medium for introducing Indonesian animals to foster the nation\u27s love for children.Design/methodology/approach: AR applications are built using markers. AR application development uses the MDLC method, which consists of six stages, namely concept, design, material collection, manufacture, testing, and distribution.Findings/result: This research resulted in the application of Augmented Reality Animal Recognition. The results of the tests that have been carried out using the similarity test of 92% for testing the similarity of 3D objects on animals. SEQ testing with an average result of 91.18 on a scale of 10, so it can be concluded that the application has met the needs of users.Originality/value/state of the art: The development of this application focuses on AR applications with models of Indonesian animals and explanations of the characteristics of these animals
Implementation of Design Thinking for Web Based E-Voting Student Organization in Nahdlatul Ulama University of Yogyakarta
Get PDFPurpose: implement design thinking for web based E-Voting Student Organization in Nahdlatul Ulama University of YogyakartaDesign/methodology/approach:the method which used in this research is design thinking. The steps in this method are emphatize, define, ideate, prototype, and testFindings/result:the development of E-Voting is succesfully made according to user needsOriginality/value/state of the art:E-Voting web-based for student organization in Nahdlatul Ulama University of Yogyakart
Analysis of the usability quality of vocational high school websites using a user satisfaction approach
Get PDFPurpose: knowing the extent to which aspects that affect the level of user/visitor satisfaction in using the website.methodology: the method used is usability approach to measure website visitor satisfaction using Structural Equation Model (SEM) theory and SmartPLS v.3.2.9 software.Findings/result: found several variables that influence user satisfaction, and found variables that had no effect, even having a negative dependency value. In addition, it also produces priority recommendations for website improvement to meet user satisfaction.Originality: this study uses the palmer model usability approach [13] and the structural equation model. Which is different from previous research using the webqual method and Importance Performance Analisys [3
Identification Of Keywords That Impact Of Increasing The Click Through Rate Of Online Advertising On Search Engines
Get PDFPurpose: To identify keywords that can be chosen to increase CTR on the website so that the potential revenue of targeted prospects through search engines is higher.Design/methodology/approach: This study applies the weighted product method based on the criteria that will be determined to find the best keyword list.Findings/result: The results of identification by ranking using the weighted product method based on the criteria C1, C2, and C3 resulted in an average increase in CTR of 16.18% to 22.92%. With this increase, business owners can be more efficient in the online advertising process.Originality/value/state of the art: The identification of keywords that can be chosen to increase CTR on a website by ranking using the weighted product method has never been done by previous researchers.
Implementation Of The Double Exponential Smoothing Method In Determining The Planting Time In Strawberry Plantations
Get PDFPurpose: This research aims to provide recommendations for planting season based on predictions of rainfall, air temperature, and wind speed based on the website.Design/methodology/approach: This study implemented the Double exponential smoothing to predict rainfall, air temperature, and monthly wind speed one year in the future using past data.Findings/result: This study has succeeded in providing recommendations for planting season. Based on the results of the accuracy calculation between the prediction results and the actual data using the Mean Absolute Percetage Error (MAPE), each has a forecast error value of 30.69% for rainfall, 0.63% air temperature, and 5.89% wind speed. Originality/value/state of the art: Research related to the application of Double exponential smoothing to determine the planting period. Based on the results of the accuracy calculation between the prediction results and the actual data using Mean Absolute Percetage Error (MAPE), this has never been done in previous studies
Analysis of the AHP-WP Method in the Decision Support System for the Assessment of Outstanding Students at ITEKES Bali
Get PDFPurpose: This study aims to analyze and determine the effectiveness of the combination of decision-making methods in the selection of outstanding students using the Analytical Hierarchy Process (AHP) and Weighted Product (WP) methods.Design/methodology/approach: A quantitative approach is used to analyze the combination of AHP and WP methods in determining outstanding students. The ranking results were analyzed using Mean Absolute Percentage Error (MAPE).Findings/result: This research produces a combination analysis of the AHP and WP decision-making methods, so that it can be used for implementation into information systems.Originality/value/state of the art: The difference between this study and previous studies is the combination of methods used in this study. An analysis of the effect of several variables in increasing accuracy is also produced