Articles
1,196 Documents
<![CDATA[Detection of Room Cleanliness Based on Digital Image Processing using SVM and NN Algorithm ]]>
<![CDATA[suparni, Suparni]]>;
<![CDATA[Rachmi, Hilda]]>;
<![CDATA[Kaafi, Ahmad Al]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11479
<![CDATA[A clean environment can prevent us from disease and can increase productivity. A neat and clean room arrangement can affect health, avoiding the possibility of stress, lethargy, and depression. The room recognition process based on its neatness is carried out through a process of matching and comparing the images that are used as training and testing sets. Technological developments make it possible to detect room conditions through image. Detection uses image processing by classifying images into 2 categories, clean and messy. It has been widely used in various fields, one of which is hospitality. In determining the clean room and messy room has problems due to image quality, different lighting, and image similarity. This study aims to detect clean and messy spaces by comparing the Support Vector Machine and Neural Network methods on a dataset of 199 images. Based on the test, the highest accuracy classification value was 98.0% for the Neural Network method with an AUC of 0.999]]>
<![CDATA[Sentiment Analysis About COVID-19 Booster Vaccine on Twitter Using Deep Learning ]]>
<![CDATA[Elly Indrayuni]]>;
<![CDATA[Achmad Nurhadi]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11485
<![CDATA[The rapid spread of COVID-19 cases to various countries has made the COVID-19 outbreak a global pandemic by the World Health Organization (WHO). The effect of the designation of COVID-19 as a pandemic has prompted the government to take preventive action against vaccination, as well as the WHO which has asked the public to immediately get a third or booster dose of vaccine. Various responses regarding the COVID-19 booster vaccine continue to emerge on social media such as Twitter. Twitter is often used by its users to express emotions about something either positive or negative. People tend to believe what they find on social networks, which makes them vulnerable to rumors and fake news. Sentiment analysis or opinion mining is one solution to overcome the problem of automatically classifying opinions or reviews into positive or negative opinions. In this study, the Deep Learning algorithm was used to analyze public opinion sentiment regarding the COVID-19 booster vaccine on Twitter. The data collection method used is crawling data using an access token obtained from the Twitter API. Meanwhile, to evaluate the model, the K-fold Cross-Validation method is used. The results of testing the model obtained the highest accuracy value at iterations = 10, which is 82.78% with AUC value = 0.836, precision = 83.33% and recall = 95.89%.]]>
<![CDATA[The application of online practicum in assisting learning process of database courses using Waterfall method ]]>
<![CDATA[Suryadi, Andri]]>;
<![CDATA[Sufandi, Unggul Utan]]>;
<![CDATA[Nurdiana, Dian]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11486
<![CDATA[The Open University is a State University prioritizing independent learning. Independent learning would certainly succeed if the students owned a strong determination in effectively and efficiently manage their time. In the Information Systems Study Program curriculum, there are several practical courses that must be conducted offline. In 2019 however, the phenomenon of the COVID-19 pandemic outbreak requiring all educational units to carry out learning from home had impacted on the learning process, especially the implementation of practicum at the Open University. The implementation of practicum activities usually held in collaboration with several institutions has become constrained. This triggered the possibility of not achieving student learning outcomes related to learning materials learned through practicum. Therefore, as an alternative solution, an application is required that could assist the students in carrying out practicum learning activities independently which is adapted to each teaching material. This practical application would be developed in a study using the Waterfall method consisting of analysis, design, implementation, testing and maintenance. From the results of test using the System Usability Scale (SUS), the score obtained is 64.44 (margin low). This means that the application online practicum can be used but does not meet the requirements to be implemented into existing learning systems until it gets a score of more than 80 (Acceptable).]]>
<![CDATA[Perfomance analysis of Naive Bayes method with data weighting ]]>
<![CDATA[Afdhaluzzikri, Afdhaluzzikri]]>;
<![CDATA[Mawengkang, Herman]]>;
<![CDATA[Sitompul, Opim Salim]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11516
<![CDATA[Classification using naive bayes algorithm for air quality dataset has an accuracy rate of 39.97%. This result is considered not good and by using all existing data attributes. By doing pre-processing, namely feature selection using the gain ratio algorithm, the accuracy of the Naive Bayes algorithm increases to 61.76%. This proves that the gain ratio algorithm can improve the performance of the naive bayes algorithm for air quality dataset classification. Classification using naive bayes algorithm for air quality dataset. While the Water Quality dataset has an accuracy rate of 93.18%. These results are considered good and by using all the existing data attributes. By doing pre-processing, namely feature selection using the gain ratio algorithm, the accuracy of the Naive Bayes algorithm increases to 95.73%. This proves that the gain ratio algorithm can improve the performance of the naive bayes algorithm for air quality dataset classification. Classification using Naive Bayes algorithm for Water Quality dataset. Based on the tests that have been carried out on all data, it can be seen that the Weight nave Bayes classification model can provide better accuracy values because there is a change in the weighting of the attribute values in the dataset used. The value of the weighted Gain ratio is used to calculate the probability in Nave Bayes, which is a parameter to see the relationship between each attribute in the data, and is used as the basis for the weighting of each attribute of the dataset. The higher the Gain ratio of an attribute, the greater the relationship to the data class. So that the accuracy value increases than the accuracy value generated by the Naïve Bayes classification model. The increase in accuracy in the Naïve Bayes classification model is due to the number of weights from the attribute selection in the Gain ratio.]]>
<![CDATA[Optimization of Transaction Database Design with MySQL and MongoDB ]]>
<![CDATA[Mumtahana, Hani Atun]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11528
<![CDATA[Database is one of the most important parts in running an application. Databases can be used to store data. However, in running an application, the selection of an appropriate database needs to be considered, so that the resulting information can be in accordance with user needs. In developing applications, more people use RDBMS design which has a very structured nature, but technological developments have introduced NoSQL as a database development method. In this research, MySQL and MongoDB databases will be tested in transaction processing. The tests carried out include comparisons of database designs, comparisons of defining table structures, comparisons of running time in the insert, update, delete, search processes. The test results show that MongoDB has a simpler table description structure than MySQL. The results of the running time test show that MongoDB has a faster running time difference than MySQL. In the insert process there is a time difference of 0.005625 sec, update 0.001688 sec, delete 0.00075 sec and search 0.006875 sec.]]>
<![CDATA[Development of Android-Based Early Reading Learning Media ]]>
<![CDATA[Hapsari, Estuning Dewi]]>;
<![CDATA[Yuda, Yoga Prisma]]>;
<![CDATA[Mubarok, Yoga Akmal]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11549
<![CDATA[Early reading is a skill that students should have. This skill becomes a provision for the next stage of skills .Learning to recognize letters, especially early reading in Golan Kindergarten during the pandemic, experienced problems. Students feel less interested when the learning process is carried out conventionally. In addition, parents also have difficulties when it comes to delivering material to children. Through the use of android-based learning media, the learning process is expected to attract students. The method developed the Borg & Gall model, which consisted of ten stages. The data collection techniques used include observation, interviews, and questionnaires. Observation is used to find out the learning conditions in schools. Interviews, conducted with teachers to find out the use value of the media created. Meanwhile, the questionnaire is used as a reference to find out the level of needs in schools. The resulting learning media is tested through media expert validation tests and practicality tests. Validation of media experts to assess whether media is suitable for use as an alternative to learning media in schools. Practicality test, used to assess the level of practicality of the resulting medium. The results of media expert validation obtained a percentage of 81.5, stating that the media was valid. The practicality test was 8,262, and the mean score of students was 77. The two results presented that the android-based learning media for early reading was feasible]]>
<![CDATA[Membandingkan Performa Algoritma K-Means dan DBScan Untuk Text Clustering Ulasan Produk ]]>
<![CDATA[Andriyani, Fitri]]>;
<![CDATA[Puspitarani, Yan]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11569
<![CDATA[The purpose of this study was to compare the accuracy performance of the K-Means and DBScan algorithms in clustering product reviews. This comparison evaluated to determine which algorithm is better in terms of accuracy. The two algorithms were chosen because they have different methods of clustering, K-Means uses centroid-based while DBScan uses density-based. Text clustering results can be implemented on e-commerce platforms, marketplaces or product review platforms. This can help customers in deciding what product they will buy. One of the factors that customers have difficulty in determining what product they will buy is the number of reviews that each product has, and the difficulty in concluding the advantages of each product that will be matched their needs or desires. With text clustering, it can be easier and faster for customer to determine whether the product is worth buying or not based on the product reviews they read. The data set used in this study is a review of the Cetaphil Facial Wash product from the Female Daily website. Firstly, data set goes through the Text Pre-Processing stage; then it will be clustered using two algorithms, K-Means and DBScan. After that, the results of the clustering of the two algorithms calculated for their accuracy performance and the performance results obtained. From the results of this study, it concluded that, in the review clustering of Cetaphil Facial Wash products, DBScan has 99.80% accuracy, which higher to compare with K-Means with only has 99.50% accuracy.]]>
<![CDATA[APLIKASI BUILDING MANAGEMENT ]]>
<![CDATA[Sukarya, Robby Rohman]]>;
<![CDATA[Yuliana, Ade]]>;
<![CDATA[Taryana, Yudi]]>;
<![CDATA[Samuel, Hizkia]]>;
<![CDATA[Turnip, Ferlin Firdaus]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11443
<![CDATA[One of the facilities and assets owned by Bank Indonesia is an official residence intended for permanent employees, office buildings, and other facilities such as borrowing rooms and goods that can be used by employees to support office activities. But in the implementation of maintenance of official houses and office buildings as well as the process of requesting room loan and goods still done manually. Therefore, a Building Management application is needed that can help the maintenance activities of official house buildings and office buildings as well as the process of requesting the loan of rooms and goods. Building Management application is a software that is used for building maintenance and management of all building needs including borrowing space and goods in an office building. This study aims to accelerate the process of requesting repairs to official office buildings and office buildings as well as borrowing rooms and goods. In addition, this application also generates automatic report recording output. The method in this study use V-Model is an extension of the waterfall model and is based on the association of the testing phase to each appropriate development phase. The result in this study is application to be built is based on the website using the CodeIgniter framework and the V Models system development method with stages arranged starting from verification which contains the needs analysis stage, design to the coding phase and also the validation process that contains testing of the application to determine application functionality and also know the level application usability for the user.]]>
<![CDATA[Analysis of e-Service quality performance at BKPSDM Lubuklinggau web-based using E-Govqual and Importance Perfomance Analysis (IPA) methods ]]>
<![CDATA[Astuti, Tri Puja]]>;
<![CDATA[Elmayati, Elmayati]]>;
<![CDATA[Hasanah, Tri]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11444
<![CDATA[The Agency for Personnel and Human Resources Development (BKPSDM) uses the E–Kinerja service system. E-performance is a system for measuring employee performance. E- Govqual is a method that has attributes for assessing service quality. E-Government Importance Performance Analysis (IPA) is an assessment analysis method to measure the quality of a service based on the level of importance and level of performance perceived by the user. The research was conducted with the concept of measuring service quality in the form of electronic services focused on a government website called E-Government Quality (E-Govqual). The results of the gap analysis at this stage are carried out to determine the level of gap or difference in expectations between user interests and perceived system performance or user perceptions of the service quality of the E-Kinerja system. In the analysis of the level of conformity, the measurement is carried out by calculating the comparison between the reality of the service perceived by the user and the expectation of the service that the user wants. Furthermore, the analysis process is carried out with Importance Performance Analysis (IPA) using quadrant analysis whose results are mapped into Cartesian with the importance and performance axes. Based on the final results, the calculation shows the average level of conformity of each indicator in the four E-Govqual variables. From the table, it can be seen that all the average values of the suitability level of the 4 dimensions are 101%. These results indicate that the performance of each attribute in the E-Kinerja application can meet the expectations of users. Based on the final result of the variable calculation, the largest gap occurs in the Trust variable with an average value of 0.05, then the smallest gap is in the Reliability Variable with an average value of -0.05 variable.]]>
<![CDATA[Product Recommendation System Application Using Web-Based Equivalence Class Transformation (Eclat) algorithm ]]>
<![CDATA[Gito Resmi, Mochzen]]>;
<![CDATA[Hermanto, Teguh Iman]]>;
<![CDATA[Ghozali, Miftah Al]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i3.11454
<![CDATA[The use of saved transaction data can provide a lot of knowledge that useful to the company in making policy and find the strategy in Alfamidi. In applying that goal, that is using Market Business Analysis. One of the techniques of Data Mining is Association Rule, which is the procedure of Market Basket Analysis to find the customer buying patterns. This pattern can be one of the ways in making policy and business strategy. One pattern determined by two parameters, they are support (support value) and confidence (certainly value). This analysis used algorithm Equivalence Class Transformation (ECLAT). One of the patterns resulted from analysis to the 30 transaction data with 12 category items. As an instance, if we buy strawberry jam then buy essence of bread with confidence value = 1%. The results obtained an also be used in helping the Alfamidi to help in determine the inventory decisions. So, the conclusion may be taken if consumers could buy strawberry jam then bought essence of bread simultaneously, then the Alfamidi should at least maintain the availability stock of both these items in order to remain the same.]]>
