Sinkron : jurnal dan penelitian teknik informatika
Not a member yet
1261 research outputs found
Sort by
Supervised Learning from Data Mining on Process Data Loggers on Micro-Controllers
No full textIn processing data science, data is needed as input. Sometimes the data needed does not exist in public data, this is where the purpose of this research is made. The acquisition process is so important to process information into data. After that, the data is processed to make a decision. Micro-controller in controlling conditions, such as temperature, and humidity are very common devices, and a lot of research has been done. Sometimes discussing it only shows how to create a series and save it on online platforms, such as firebase, tinger.io, and many others online platforms. So that the process of storing data on an external or online platform is an advantage for platform providers, where platform providers do not need to do business and get data for free. This is without realizing the researchers who have produced a micro-controller device. Many platforms for storing data range from hardware and software devices. Some devices are paid or open source. This research uses software tools that are open source. Because using open source-based tools it will be easy to develop and for further research purposes. The development of the following research by entering code into a micro-controller system or what is called an embedded system. Data is a very valuable asset. Because data is one of the most important components in processing in data science. And it is better to take care of the data logger. This research uses Arduino as a micro-controller and ultrasonic distance sensor and potentiomete
Facial Micro Expression Recognition for Feature Point Tracking using Apex Frames on CASME II Database
No full textMicro-expressions are facial expressions that occur inadvertently to hide true feelings (emotional leaks). Although previous studies used the entire face area and all frames in the video dataset, this resulted in relatively long computation time and data redundancy. The main contribution of this research is to apply recognition micro-expression analysis using a comparison of apex frames with manual (handcrafted) and random sampling of frames and applying feature point tracking to the brow area and corners of the lips. The method for forming feature points in the facial area uses Discriminative Response Map Fitting (DRMF), then facial feature points are tracked using Kanade-Lucas-Tomasi (KLT). This feature point tracking produces motion feature data as feature extraction data. Finally, a comparative analysis of the classification method using the Support Vector Machine (SVM) and MLP-Backpropagation was conducted using the CASME II dataset. The experimental results of this study show significant results with an accuracy of 81.3% on MLP-Backpropagation and an average computing time of 1.45 seconds for each video. From the results of this study, information on the apex phase can contribute information that is very important for facial micro-expression recognition
Usability Evaluation of SIDUMAS Badung Using Think Aloud, Heuristic Evaluation and SUS
No full textThis study aims to 1) find out the problems that occur in the Badung Regency community complaint system (SIDUMAS) by conducting a usability evaluation using the think-aloud method, heuristic evaluation and system usability scale, 2) conduct a usability evaluation on the community complaint system can determine the level of application usability and determine recommendations for improvements needed by the Badung community complaint system (SIDUMAS). Respondents who participated in this study were Badung people consisting of 5 usability experts and 30 general public. Determination of respondents in this study based on the criteria of the method used. The data in this study were obtained through usability evaluation results on the public complaint application questionnaires and data from interviews with respondents. The method used to evaluate the public complaint system is a combination of 3 methods, namely think aloud, heuristic evaluation and system usability scale which will produce an assessment to determine the usability and recommendations for improvements to the Badung SIDUMAS system. The results showed that: (1) Using the think-aloud method, it was found that the problems experienced by users of the community complaint system application on average experienced the same problems in the test. The results of research with heuristic evaluation found that there is 1 problem that has the highest severity rating where the problem must be fixed immediately. The results of the calculation of the average system usability scale score on user satisfaction obtained a score of 78 with acceptability ranges in the acceptable category. Furthermore, for the percentile rank score, the value obtained is 78 so it is in the grade B category. (2) Making recommendations for improvement in the study focused on changing the layout on the page and navigation menu on the results of data causing errors experienced by users
Design Of Automatic Fire Detection and Extinguishing Devices Using Arduino
No full textA robot is a series of hardware and software in the form of a driving program. Robots are not only used in industry; in developed countries, robots are widely used to help with household chores. Many jobs that require a lot of energy are high-risk or dangerous, one of which is detecting and extinguishing fires. Fires can be avoided if the fire can be extinguished before it spreads. When the fire has spread, extinguishing it will be difficult and high-risk. Fires can cause huge losses of both property and lives that cannot be saved. The problem can be reduced if the source of the fire can be quickly found and extinguished. In this research, a fire extinguisher robot will be designed with an Arduino Mega 2560 and an infrared flame detector to detect the presence of fire. This robot is accompanied by an HC-SR04 ultrasonic sensor so that the robot can walk automatically without hitting obstacles because this robot aims to walk down hallways such as areas in the house or in any area that has a hallway for the robot's path. This research aims to implement Arduino for the control of the ultrasonic sensor and the movement of the fire extinguisher robot. The use of an Arduino micro-controller on the fire extinguisher robot is expected to make the robot move steadily and avoid obstacles in the hallway
Weather Forecast In Medan City With Hopfield Artificial Neural Network Algorithm
No full textMany aspects are very influential for the continuity of Indonesian society, especially Medan. One of the aspects that affect the continuity of the people of Medan is the weather. Weather plays an important role in various sectors, such as agriculture, aviation, and many other sectors. The Meteorology, Climatology and Geophysics Agency (BMKG) is always trying to develop their innovations to be able to provide accurate weather information to the public. To assist the process of disseminating weather information to the public in Medan City, we need a Weather Forecast application that uses Website-based computer technology so that it can help disseminate weather information easily and effectively which is generated through the support of the Hopfield method by connecting the application with BMKG data. Based on the results of this study, a weather forecasting application was successfully built to help disseminate weather information in Medan City to all Medan City people who want to get information about the weather
COMPARISON OF K-N EAREST NEIGHBOR AND NAÏVE BAYES ALGORITHMS FOR PREDICTION OF APTIKOM MEMBERSHIP ACTIVITY EXTENSION IN 2023
No full textSo far APTIKOM as the Informatics and Computer Higher Education Association has provided many opportunities for registered members to participate in discussions on the development of science among fellow association members, access to various professional experts, as well as technical and non-technical guidelines in the field of education. With the various opportunities above, it is hoped that all members will support the activities of each member who has joined or has just joined so that a good association can be created. This study aims to find out about the problems that occur in APTIKOM, namely members who have registered as members but rarely renew their membership which results in data accumulation in APTIKOM. This research method uses the k-nn and naïve Bayes algorithms by using data sets from 2012 to 2022. The dataset used is APTIKOM member data and has 5 attributes namely name, gender, last education, institution and validation secret. To calculate the research test using a rapid miner. The purpose of this study is to predict whether in the following year there will be a membership renewal process for all APTIKOM members who have been recorded from 2012 to 2022. Furthermore, the results of this study have a different level of accuracy. Where for k-nn the resulting accuracy is 94.00% and for the result of naïve Bayes is 91.35%
Tenant ShopeePay Fintech Application Acceptance Analysis Using TAM
No full textThis study aims to determine the analysis of tenant acceptance on the ShopeePay application in PTC using the Technology Acceptance Model. The type of data in this study is quantitative. Sample determination using a random sampling technique or purposive sampling obtained a sample of 56 tenants. Based on the results of the analysis using SPSS to find the influence between variables on information users, there is a relationship between perceived usefulness (X1) and image (X2) and tcount > ttable (5.889 > 1.997), there is a relationship between perceived usefulness (X1) and perceptions of usability (X8) and tcount > ttable (3.895 > 1.997), there is no relationship between image (X2) to perceptions of usability (X8) and tcount < ttable (1.871 < 1.997), there is a relationship between self-confidence (X3) to perceptions of ease of use (X7) and tcount > ttable (3.867 > 1.997), there is no relationship between anxiety (X4) to perceptions of ease of use (X7) and tcount > ttable (-1.041 < 1.997), there is a relationship between conditional facilitating (X5) and perceptions of ease of use (X7) and tcount > ttable (6.368 > 1.997), there is a relationship between perceptions of pleasure (X6) to perceptions of ease of use (X7) and tcount > ttable (10.825 > 1.997), there is a relationship between perceptions of ease of use (X7) to perceptions of usability (X8) and tcount > ttable (8.790 > 1.997)
Sentiment Analysis Of Hotel Reviews On Tripadvisor With LSTM And ELECTRA
No full textThis study examines the importance of hotel review data analysis and the use of Natural Language Processing (NLP) technology in predicting hotel review sentiment. In this study, deep learning models such as Long Short-Term Memory (LSTM) and Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA) are used to predict hotel review sentiment in Indonesian. Hotel review data was obtained through a data scraping process with webscraper.io from the Tripadvisor website and a total of 977 hotel review data were obtained from Grand Mercure Maha Cipta Medan Angkasa. Before the sentiment prediction process is carried out, hotel review data must go through the text preprocessing stage to remove punctuation marks, capital letters, stopwords, and a lemmatizer process is carried out to facilitate further data processing. In addition, sentiments that were previously unbalanced need to be balanced through the undersampling process. The data that has been cleaned and balanced is then labeled as negative (0), neutral (1) and positive (2) sentiments. The test results show that the ELECTRA model produces better performance than the LSTM with an accuracy of 47% by ELECTRA and 30% by LSTM
Analysis of the SVM Method to Determine the Level of Online Shopping Satisfaction in the Community
No full textOnline shopping is an activity of buying goods done online (virtual). This online shopping process is done because it doesn't waste a lot of time. With online shopping, it is very easy for people. Just need open mobile phone view and select the desired item and then order goods and goods will be delivered to the house. But online shopping sometimes also has drawbacks which are one of the reasons people don't want to shop online, such as long shipping times, expensive shipping costs. Therefore a study was made about the level of public satisfaction in online shopping. Researchers will make a data classification about the level of public satisfaction in online shopping using the SVM method. This study aims to see the level of public satisfaction with online shopping, many or nope satisfied people when shopping online. The first step is to collect data that will be used in the data mining process. After that, data preprocessing will be carried out planning the design of the SVM method and finally the prediction process to get Classification results. Then the classification results obtained using the SVM method in data mining show that 34 people are satisfied with online shopping (for a representation result of 59.65%), 23 people are dissatisfied with online shopping (for a representation result of 40.35%). These results state that there are still many people who are satisfied with shopping online and there are some people who are dissatisfied with online shoppin
Implementation of Cyber-Security Enterprise Architecture Food Industry in Society 5.0 Era
No full textThe application of Enterprise Architecture is an important topic in the development of the food industry in the Society 5.0 Era. Enterprise Architecture is used to integrate and optimize corporate information systems so as to generate higher business value. This study aims to evaluate the effectiveness of Enterprise Architecture implementation in improving the performance of the food industry in Era Society 5.0 and implementing Cyber-Security as a defense against the system to be implemented. This study uses a case study method by collecting data from several companies in the food industry. The data collected includes information about the implementation of Enterprise Architecture, business performance, and factors that influence the successful implementation of Enterprise Architecture. The results of the study show that the implementation of Enterprise Architecture has helped companies improve their business performance, especially in terms of operational efficiency, better decision making, and the ability to adapt to changes in the business environment. Factors that influence the successful implementation of Enterprise Architecture include management support, involvement of business users, and availability of resources. In conclusion, the application of Enterprise Architecture can help the food industry in Era Society 5.0 improve its business performance. However, the implementation of Enterprise Architecture must be accompanied by strong management support, greater involvement of business users, availability of adequate resources and adequate Cyber-Security. The novelty of this research is implementing Cyber-Security as protection in implementing Enterprise Architecture