Sinkron : jurnal dan penelitian teknik informatika
Not a member yet
1261 research outputs found
Sort by
Drowsy Detection in the Eye Area using the Convolutional Neural Network
No full textDetection of a drowsy driver is an important aspect of driving safety. For this reason, it is necessary to have technology to carry out early detection before fatigue occurs. Mainly focused on driver fatigue that occurs at night. Analysis can be done quickly and accurately. These conditions can be sent via data so that they can be monitored and analyzed in real time. The results of the analysis can be sent by communication via the internet network. In addition, it functions as an early warning and can be used as logging or records that can be stored. This research does not discuss data communication but makes a prototype for detecting sleepy drivers. Prototype created using the Convolutional Neural Network Algorithm. The detection area is in the eye and testing is carried out with the brightness level of the light. In this study, building a prototype to detect signs of driver fatigue using the Convolutional Neural Network algorithm. The detection area used is in the eye, by testing at different light brightness levels. The dataset used in this study consists of a series of eye images, which are divided into two classes, namely open eyes, and closed eyes. After conducting the training process on Convolutional Neural Network, we get results of detection accuracy reaching 90%
The Implementation of Support Vector Machine Method with Genetic Algorithm in Predicting Energy Consumption for Reinforced Concrete Buildings
No full textAccurate information on energy consumption is crucial for measuring energy efficiency and savings in buildings. It refers to the energy needed to power a building at a specific time. Energy savings can reduce costs and environmental impact by lowering greenhouse gas emissions. Obtaining precise energy consumption data is essential for all parties involved in building planning, construction, and management. Over the past decades, global energy consumption in buildings has consistently increased, with HVAC systems being a significant contributor. To tackle this problem, research developed a support vector machine model with genetic algorithms to accurately predict energy consumption in buildings. Two models were tested: a standard support vector machine and a genetic algorithm-integrated support vector machine. The test results revealed that the support vector machine model achieved an RMSE value of 2.6. Additionally, the genetic algorithm optimized the parameter C and selected the most relevant predictor variables, reducing the RMSE to 1.7 and utilizing only 3 predictor variables. In the subsequent stage, parameter optimization and function selection were performed to achieve an improved RMSE value of 1.537. This research aims to enhance energy consumption prediction for reinforced concrete buildings by combining SVM and Genetic Algorithm. SVM serves as the primary prediction model, while the Genetic Algorithm is employed to determine optimal SVM parameters and relevant features. Recent studies have demonstrated that this combination yields more accurate predictions compared to standard methods. It enables more efficient energy planning, reduced operational costs, and optimized resource utilization in reinforced concrete buildings. However, it's worth noting that this implementation may require substantial processing and resource utilization, depending on the dataset's size and complexity
FREQUENCY ANALYSIS OF DELI RIVER FLOOD DISTRIBUTION PLAN USING THE GUMBEL PROBABILITY DISTRIBUTION METHOD
No full textThe Deli river basin is one of the rivers in North Sumatra Province which is in Medan City with an area of 394.88 km2 and a length of 166.01 km. Medan Maimun District which has an area of 2.98 km2 and a population density of 16,520 people/km2. Medan Mimun sub-district is one of the flood-prone areas which is drained by the Deli River. The cause of the flooding that occurred in Medan Maimun District was high rainfall so that the river flow rate increased and drainage was poor. So that the problem of flooding in the Deli river watershed, Medan Maimun sub-district, can hamper community activities, these floods can also harm and endanger the community. The flood discharge plan for each repeat period where the variable used is the maximum daily rainfall for 10 years From 2013-2022 which is sourced from the BMKG Deli Serdang. In this study using frequency analysis and then proceed with the Gumbel Probability Distribution method, Normal Distribution Log Person Type III. The result of this study with hydrological data and distribution test, the suitable method for analyzing the planned flood discharge in the Deli River is Log Person Type III that it can be flood discharge for a 2 year retention period is 12.7684672 m3/sec, 5 year return period is 12.56275855 m3/sec, 10 year return period is 15.91400029 m3/sec, 25 year return period is 16.87871678 m3/sec, 50 year return period is 17.43836748 m3/sec and a 100 year return period is 17.89619614 m3/sec.
Keywords: Rainfall, Deli River, Planned Flood Discharge
 
Finite Element Model of Rock Obstruction on Overtopping at the Coastline
No full textWave overtopping is a common phenomenon that occurs during extreme sea conditions, where water waves travel over the surface of an open structure towards the sea and pass over its crest. To prevent flooding and coastal erosion, rock structures are often constructed as wave barriers along the shore. These barriers serve as a solution to mitigate wave overtopping. One of the key factors influencing overtopping is the arrival of continuous and sufficiently high-water waves that can pass through the top of coastal defense structures. Several phase settlement methods have been developed and applied to analyze wave overtopping using the Navier-Stokes (NS) equation. By employing the finite element method, numerical solutions and simulations are sought by inputting specific parameter values. This process aims to validate the accuracy of the resulting mathematical model. To accomplish this, a program is developed based on the discretization of the model, enabling a system analysis approach. The obtained results exhibit minimal error values, thereby demonstrating optimal outcomes in terms of rock placement. The entire fluid mechanics system analysis is simulated using the COMSOL Multiphysics 5.6 program, which provides a comprehensive platform for studying and evaluating the performance of the wave barrier system
 
Decision Support System for Selection of Healthy Toddler using MOORA Method
No full textToddlers are the human stage after infancy, toddlers are one of the most important stages in the quality development of human growth. one way to develop health in toddlers is to carry out routine checks at Public Health Center. Public Health Center has not yet provided a system for selecting healthy toddlers and also requires a system for selecting healthy toddlers. Therefore a decision support system is needed to make decisions related to checking the health of toddlers. decision support system is part of a computer-based information system, which is used to make a decision, in making a decision support system the Multi Objective Optimization by Ratio Analysis (MOORA) method is used. Based on the calculations made regarding the decision to check the health of toddlers, the MOORA method uses weighting criteria and determines the type of criteria, and MOORA does not have sub-criteria weighting provisions using FMADM, FMADM weighting reduces ambiguity because the bigger the value, the better, but if the value is too large then it is not good, such as body weight. It is necessary to provide more sub-criteria so that the accuracy in ranking is better and more accurate with a scale of 0-5. The optimization value for A1 is obtained by adding the cells from A1 0.6765 + 1.0070 + 0.2626 + 0.1195 = 2.0656 and Alternatives A2, A3, A15 have the most optimal weight values with optimization values (2.3282)
Retweet Prediction Based on User-Based, Content-Based, Time-Based Features Using ANN Classification Optimized with the Bat Algorithm
No full textTwitter is one of the most popular social media platforms today for information dissemination. It is favored by the public due to its real-time information sharing capabilities. Twitter provides two important features for information dissemination: Tweets and Retweets. Tweets allow users to write messages that can be instantly shared. Each tweet can contain text, media such as images, videos, or URLs. Retweets allow users to repost someone else's tweet and distribute it to their own followers. The Retweet feature is considered an effective way to spread information, as a high number of retweets indicates that the information in the tweet is spreading quickly and widely. This research aims to predict retweets based on several features: User-Based Feature, Content-Based Feature, and Time-Based Feature. The classification method used is Artificial Neural Network, which is optimized using a Nature-Inspired Algorithm called Bat Algorithm. The evaluation results of this study show an accuracy of 86%, precision of 87.8%, recall of 93.6%, and F1-score of 90.6% without imbalance class handling. Under Undersampling condition, the accuracy is 80.8%, precision is 91.0%, recall is 81.4%, and F1-score is 85.9%. Under Oversampling condition, the accuracy is 82.4%, precision is 89.6%, recall is 85.6%, and F1-score is 87.5%. These results indicate that using user-based, content-based, and time-based features, applying Artificial Neural Network classification method, and optimizing hyperparameters using Bat Algorithm are effective in predicting retweets
The Performance of the Equal-Width and Equal-Frequency Discretization Methods on Data Features in Classification Process
No full textThe classification process often needs help with suboptimal accuracy values, which can be attributed to various factors, including the dataset's wide range of attribute values. Discretization methods offer a solution to address these issues. This study aims to compare the effectiveness of Equal-Width and Equal-Frequency discretization methods in enhancing accuracy during the classification process using datasets with varying sizes. The research employs Naïve Bayes, Decision Tree, and Support Vector Machine as classification models, with three datasets utilized: Bandung City Traffic data (3804 records), Bandung City COVID-19 cases data (2718 records), and Bandung City Dengue Fever Disease Index data (150 records). Three experimental scenarios are executed to assess the impact of the two discretization methods on accuracy. The first scenario involves no discretization, the second employs Equal-Width, and the third applies Equal-Frequency discretization. Experimental results indicate significant accuracy improvements post-discretization. The Naïve Bayes model achieved 94% accuracy for the Traffic dataset, while the Decision Tree achieved 71% accuracy for the COVID-19 dataset and an impressive 98% for the Dengue Fever Disease dataset. These outcomes demonstrate that applying Equal-Width and Equal-Frequency discretization methods addresses the challenge of wide attribute value ranges in the classification process
Pneumonia Classification Based on Lung CT Scans Using Vgg-19
No full textThis research harnesses technology for critical health applications, specifically, pneumonia detection through medical imaging. X-ray photography allows radiologists to visualize the patient's health state, including the detection of lung infections signifying pneumonia. The study's centerpiece is the application of the VGG-19 model in classifying lung CT scan images, helping discern normal from pneumonia-indicative conditions. A comprehensive preprocessing procedure is employed, entailing pixel rescaling and data augmentation techniques. To address data imbalance, a critical issue in machine learning, we incorporate the Synthetic Minority Over-sampling Technique (SMOTE). The developed VGG-19 model demonstrates impressive performance, achieving a 94.6% accuracy rate in classifying lung CT scans. This finding underscores the potential of the VGG-19 model as a reliable tool for pneumonia detection based on lung CT scans. Such a tool could revolutionize the field, providing an efficient and accurate method for early pneumonia diagnosis, thereby allowing for timely treatment
Decision Support System for Financial Aid for Underprivileged Students using the TOPSIS Method
No full textThe distribution of Financial Aid for Underprivileged Students is considered not to be on target due to the unmeasured selection process. So a decision-making system is needed that can select beneficiaries objectively. This research was conducted to assist the school in determining students who deserve this assistance. The purpose of this research is to build a decision-making system for selecting beneficiaries from poor students by applying the Technique for Order of Preference by Similarity to Ideal Solution method. The formulation of the problem is how to build a decision support system using the Technique for Order of Preference by Similarity to Ideal Solution method in selecting students who receive financial aid for underprivileged students. The method used goes through several stages, namely: determining alternatives and criteria, building a normalized decision matrix, building a weighted normalized decision matrix, determining positive and negative ideal solutions, determining the distance between ideal solutions, and determining preference values. There are 7 criteria used, namely social protection card recipients, total income, number of dependents, parental status, distance, class, and report card scores. The results showed that the highest preference value for each alternative was in alternative A3, with a score of 0.6665. While the lowest preference value is in alternative A20 with a score of 0.0719, From the results of the study, it was concluded that the Technique for Order of Preference by Similarity to Ideal Solution method can be used in making decisions on the selection of beneficiaries of poor students based on preference value rankings
Sentiment Classification of Fuel Price Rise in Economic Aspects Using Lexicon and SVM Method
No full textAfter being hit by COVID-19 for a long time around the world which resulted in the paralysis of all countries, especially the economic aspects of all countries that dropped dramatically, the world was again shocked by the conflict between Russia and Ukraine which resulted in an increase in world oil prices including in Indonesia, many people complained and opposed the government's policy of increasing fuel prices because fuel affects various aspects, including economic aspects. Based on these problems, researchers use sentiment analysis methods that aim to find out people's opinions on issues that are being discussed throughout Indonesia and this research focuses on comparing the SVM algorithm with TF-IDF feature extraction then using K-Fold Cross Validation after that it is compared with the Lexicon Inset dictionary, in this case the model with Lexicon Inset which contains weighting on each word. In this study, it was found that the dataset model using the SVM algorithm with TF-IDF feature extraction and then using K-Fold Cross Validation obtained an average accuracy of 0.85 using the SVM algorithm. While the model using the automatic labeling dataset using the Indonesian sentiment Lexicon (Lexicon Inset) obtained an average accuracy of 0.68. Classification using SVM with TF-IDF feature extraction is superior to using Lexicon Inset