Jurnal Online Informatika
Not a member yet
276 research outputs found
Sort by
Decision Support System for Employee Recruitment Using El Chinix Traduisant La Realite (Electre) And Weighted Product (WP)
Get PDFManagement of human resources (HR) is important to achieve company goals. One of the activities in HR management is recruitment, selection, and training. Recruitment and selection are usually done not using a system so that the calculations are still done manually. But by processing data using the system can produce a decision in recommending prospective employees that can have a positive impact on the company. The company selection process is carried out through two stages: administrative selection and final selection in the form of psychological test assessment, interviews, ability tests and communication. The use of the Elimination Et Choix Traduisant La Realite (ELECTRE) method in the administrative selection stage and the Weighted Product (WP) method in the final selection stage is a new discovery made to get the best decision in accordance with the required criteria. By using this method the final results will be obtained namely the recommendation of several prospective employees who are fit to work in the company. The performance results of this system reach one hundred percent, the data from the system is in accordance with the expected calculation
Product Review Ranking in e-Commerce using Urgency Level Classification Approach
Get PDFReview ranking is useful to give users a better experience. Review ranking studies commonly use upvote value, which does not represent urgency, and it causes problems in prediction. In contrast, manual labeling as wide as the upvote value range provides a high bias and inconsistency. The proposed solution is to use a classification approach to rank the review where the labels are ordinal urgency class. The experiment involved shallow learning models (Logistic Regression, Naïve Bayesian, Support Vector Machine, and Random Forest), and deep learning models (LSTM and CNN). In constructing a classification model, the problem is broken down into several binary classifications that predict tendencies of urgency depending on the separation of classes. The result shows that deep learning models outperform other models in classification dan ranking evaluation. In addition, the review data used tend to contain vocabulary of certain product domains, so further research is needed on data with more diverse vocabulary
Multiscale Retinex Application to Analyze Face Recognition
Get PDFThe main challenge that facial recognition introduces is the difficulty of uneven lighting or dark tendencies. The image is poorly lit, which makes it difficult for the system to perform facial recognition. This study aims to normalize the lighting in the image using the Multiscale Retinex method. This method is applied to a face recognition system based on Principal Component Analysis to determine whether this method effectively improves images with uneven lighting. The results showed that the Multiscale Retinex approach to face recognition\u27s correctness was better, from 40% to 76%. Multiscale Retinex has the advantage of dark facial image types because it produces a brighter image output
Failover Cluster Nodes and ISCSI Storage Area Network on Virtualization Windows Server 2016
Get PDFThe use of data in this current digital era, the traditional model of connecting the storage media with servers, cannot meet the need for fast access to a very large amount of data. Storage Area Network can be the solution because this technology can handle a large amount of storage media (TeraByte), enable to be a share of storage resources, as well as giving data access in real-time, quick, and easy. Internet Small Computer System Interface (iSCSI) is a concept of storage media that use Internet Protocol as a medium for connecting storage media and data transfer through network service. Testing of availability server in this research use failover cluster technology, after testing done, then the result is obtained, when a failure or error occurs on the primary server, the primary server role will be automatically replaced by backup server with the same resource as the main server. As for the time automatic displacement server, when an active server makes failure, then it will only take less than 5 seconds. So, it can be concluded that this technology can minimize the value of the downtime in the system
Virtual Reality Headset Implementation on Parsec Cloud Gaming Platform
Get PDFVirtual reality (VR) based games are a type of game that provides immersive gaming experience, allowing players to dive into the virtual world of the game being played. VR-based games require a high minimum computer specification, so thin clients cannot play VR-based games properly. This research aims to see how to enable thin computers to play VR-based games by utilizing cloud gaming technology. Using a high specification computer as a server, an android device as a VR headset, this Final Project implements a VR headset device so that it can be used in conjunction with cloud gaming services to be able to play VR-based games on thin computers and see how well the implementation by seeing the result from computer resources used and the Quality of Services. With Parsec cloud gaming services, the application carried out in this Final Project can run well on computers with low specifications. CPU usage on the client computer when the service is running is high at 91% usage, with 2818 MB RAM usage. Quality of Service is obtained when setting the highest quality preset, with a throughput of 16MB with a delay of about 2 ms. VR games that are played can run well with a minimum bandwidth of 15 Mbps selected from the Frame per Second (FPS) results obtained to reach 56 FPS with medium quality settings
Embedding a Blockchain Technology Pattern Into the QR Code for an Authentication Certificate
Get PDFIn the disruptive 4.0 era that emphasizes technological sophistication, blockchain is present as a technology that increasingly influences human life, helping humans in all aspects, including education. The role of blockchain technology in the world of education is to test the validity of diplomas, the increasing number of fake diplomas for an interest, both for work and continuing education to a higher level. The purpose of this research with the implementation of blockchain is expected to make it easier for users to verify the authenticity of a diploma. This study uses the SWOT analysis method to identify all possibilities that exist in blockchain technology. The final result of this research, the system will print a physical certificate in the form of paper in general, then the certificate will be printed a QR code. To verify numeric code on QR Code via scanning on smartphone or QR Reader. It is hoped that the blockchain technology applied to digital assets can reduce cases of forgery of diplomas and other important documents
Sentiment Analysis on Social Distancing and Physical Distancing on Twitter Social Media using Recurrent Neural Network (RNN) Algorithm
Get PDFThe government is seeking preventive steps to reduce the risk of the spread of Covid-19, one of which is social restrictions that have become popular with social distancing and physical distancing. One way to assess whether the steps taken by the government regarding social and physical distancing are accepted or not by the community is by conducting sentiment analysis. The process of sentiment analysis is carried out using a variant of the Recurrent Neural Network (RNN), namely Long Short-Term Memory (LSTM). In this study, the results obtained from the sentiment analysis, where the public response to social distancing and physical distancing has more positive sentiments than negative sentiments. To measure the accuracy level of sentiment analysis using the Recurrent Neural Network (RNN) algorithm and evaluation of the modeling is done using confusion matrix where the results obtained for the training dataset are 89% accuracy, 89% recall, 89% precision, and 89% F1 Score. Meanwhile, for the test dataset, an accuracy of 80% was obtained, a recall of 79%, a precision of 81%, and an F1 score of 80%
The Design of Population Data Application Using Unified Modeling Language
Get PDFPopulation data collection at the sub-district level still uses a manual system. It is causing less efficient time. In this study the application of population data is generated in the sub-district, using web applications and using the Unified Modeling Language design. With the above considerations, we need a system that can solve population data problems. With this application, it is expected that it will facilitate the processing of population data. This new application can accelerate the process of population registration with the help of human resources who can run it. Advice needed human resources that can run the application properly
An Analysis of Spam Email Detection Performance Assessment Using Machine Learning
Get PDFSpam email is very annoying for email account users to get relevant information. Detection of email spam has actually been applied to email services for the public with various methods. But for the use of a limited number of company\u27s e-mail accounts, not all e-mail servers provide spam e-mail detection features. The server administrator must add a separate or modular spam detection feature so that e-mail accounts can be protected from spam e-mail. This study aims to get the best method in the process of detecting spam emails. Some machine learning methods such as Logistic Regression, Decision Tree, and Random Forest are applied and compared results to get the most efficient method of detecting spam e-mail. Efficiency measurements are obtained from the speed of training and testing processes, as well as the accuracy in detecting spam emails. The results obtained in this study indicate that the Random Forest method has the best performance with a test data speed of 0.19 seconds and an accuracy of 98%. This result can be used as a reference for the development of spam detection using other methods
Assessment of Readiness and Usability of Information Systems Use
Get PDFThe assessment of the use of information systems has been carried out by many researchers. This research was conducted in Private Universities in Indonesia, which currently involve many information systems in many ways, especially those related to the management of Higher Education, by measuring the readiness and usability of the use of information systems with models that I build from the integration of two models. The results of the measurement of this study were obtained from the distribution of questionnaires, there were 47% of respondents who filled 61-80% of the level of IS usage and 68% of respondents stated their readiness in the level of readiness to use IS. The stage consists of evaluating reflective measurement models and structural model assessments. Evaluating reflective measurement in evaluating internal consistency reliability using Composite Reliability, Reliability Indicator, Convergent Validity, and Discriminant Validity, finally concluded that the use of the Readiness and Usability integration model can be forwarded to a more complex research stage and can use the questionnaire