Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
Pemetaan Pelanggan dengan LRFM dan Two Stage Clustering untuk Memenuhi Strategi Pengelolaan
No full textMaibus is a company of transportation services located in Bali. Transaction data that is owned has not been managed properly. This results in data accumulation and only as a turnover calculation, so LRFM and clustering methods are needed to assist the calculation and processing data in fulfilling customer management strategies. The research was conducted by collecting and understanding data, preprocessing, applying LRFM (Length,Recency,Frequency,Monetary), normalizing LRFM, evaluating the number of clusters with Davies Bouldin Index (DBI), clustering with K-Means, and analyzing cluster results. The data used is transaction data from January 2017 to December 2018 with a total of 14.292 data. The clustering method with the K-means algorithm helps in mapping customers based on transaction data. DBI was used to determine the optimal number of clusters and LRFM used to test the determination of variables in determining customer behavior and loyalty. The results of testing 7.193 invoice using 5 clusters with DBI value is 0.135. The result of customers in cluster 0,2,4 are new customer groups with the proposed strategy is enforced strategy, while the customer in cluster 1 and 3 are lost customers with the proposed strategy is let-go strategy that refers to the customer value and customer loyalty matrix.
Maibus merupakan perusahaan di bidang jasa transportasi yang berlokasi di pulau Bali. Data transaksi yang dimiliki perusahaan belum dikelola dengan baik. Hal itu mengakibatkan penumpukan data dan hanya sebagai perhitungan omset, maka diperlukan metode LRFM (Length, Recency, Frequency, Monetary) dan clustering untuk membantu perhitungan dan pengolahan data pelanggan dalam memenuhi strategi pengelolaan pelanggan. Penelitian dilakukan dengan mengumpulkan dan memahami data, preprocessing, menerapkan LRFM, normalisasi LRFM, evalusi jumlah cluster dengan Davies Bouldin Index, clustering dengan K-Means, dan analisis hasil cluster. Data yang digunakan yaitu data transaksi dua periode Januari 2017 hingga Desember 2018 dengan total 14.292 data. Metode clustering dengan algoritma K-means membantu dalam pemetaan pelanggan berdasarkan data transaksi. Davies Bouldin Index dilakukan untuk menentukan jumlah cluster yang optimal dan LRFM digunakan sebagai penguji penentuan variabel dalam menentukan perilaku dan loyalitas pelanggan. Tujuan penelitian ini dilakukan untuk mengetahui kelompok dan jenis pelanggan yang memiliki potensial menguntungkan bagi perusahaan dan mengusulkan strategi marketing yang tepat bagi masing – masing kelompok pelanggan. Pengujian 7.193 data faktur transaksi dengan menggunakan hasil penentuan jumlah k-cluster yang optimal yaitu 5 cluster dengan nilai Davies Bouldin Index adalah 0.135 menghasilkan dua kelompok pelanggan dan dua strategi marketing yang berdasarkan customer value matrix dan customer loyalty matrix. Hasil yang diperoleh dalam pengelompokan pelanggan pada cluster 0, cluster 2, cluster 4 merupakan kelompok pelanggan new customer dengan strategi yang diusulkan adalah enforced startegi, sedangkan kelompok pelanggan pada cluster 1, cluster 3 termasuk kelompok pelanggan lost customer dengan strategi yang diusulkan adalah let-go strategi
Management Administration Smartphone Application as a Strategy to Increase Accreditation Score in Primary Healthcare Facilities
Get PDFHealth facility accreditation has been in great demand in recent years. Mobile applications can serve as a tool for community healthcare center’s (Puskesmas) to assess the value of their accreditation, especially regarding administration and management. In the context of preparation for accreditation, it can be used as a self-assessment tool for elements of management administration. This case-based article focuses on smartphone application development using the input-process-output-outcome scheme as a framework. We developed a checklist and assessment for the management administration component by reviewing Permenkes No. 46 the Year 2015 concerning Puskesmas accreditation. This is the first available mobile application on the Google Play Store, targeting Puskesmas staff to improve the quality of administration and management services based on accreditation criteria. This smartphone application functions as an independent assessment tool for Puskesmas to complete the accreditation criteria as stated in the regulation of the minister of health. About 20 Puskesmas staff showed a very good response and positive. All stated that they were very helpful and satisfied with this application, so they will continue to use and distribute it to other Puskesmas staff.
 
Identification of Malaria Parasite Patterns With Gray Level Co-Occurance Matrix Algorithm (GLCM)
No full textThe results of the test using 5 data of malaria parasite test imagery found that image 1 has an average accuracy value of the energy of 0.55627, homogeneity average of 0.8371, PSNR of 6.1336db, and MSE of 0.24358. Image 2 has an average energy accuracy value of 0.22274, an average Homonegity of 0.98532, a PSNR of 6.1336db, and an MSE of 0.24358. Image 3 has an energy average accuracy value of 0.28735, a Homonegity average accuracy value of 0.9793, a PSNR of 6.133db, and an MSE of 0.24358. Image 4 has an energy average accuracy value of 0.32907 and an average homogeneity accuracy value of 0.97073, PSNR 6.133db, and MSE 0.24358. Image 5 has an average accuracy value of 0.74102, Homonegity average of 0.99844, PSNR of 6.133db, and MSE of 0.4358. Image 6 has an accuracy value of 0.34758 energy, an average accuracy value of homogeneity of 0.99129, a PNSR of 6.133db, and an MSE of 0.24358. Obtained the rule if the average value of energy > = 0.50 then the pattern of malaria parasites is very clear, namely Image 1 and image 5 with a pattern of malaria parasites is very clear.The results of the test using 5 data of malaria parasite test imagery found that image 1 has an average accuracy value of the energy of 0.55627, homogeneity average of 0.8371, PSNR of 6.1336db, and MSE of 0.24358. Image 2 has an average energy accuracy value of 0.22274, an average Homonegity of 0.98532, a PSNR of 6.1336db, and an MSE of 0.24358. Image 3 has an energy average accuracy value of 0.28735, a Homonegity average accuracy value of 0.9793, a PSNR of 6.133db, and an MSE of 0.24358. Image 4 has an energy average accuracy value of 0.32907 and an average homogeneity accuracy value of 0.97073, PSNR 6.133db, and MSE 0.24358. Image 5 has an average accuracy value of 0.74102, Homonegity average of 0.99844, PSNR of 6.133db, and MSE of 0.4358. Image 6 has an accuracy value of 0.34758 energy, an average accuracy value of homogeneity of 0.99129, a PNSR of 6.133db, and an MSE of 0.24358. Obtained the rule if the average value of energy > = 0.50 then the pattern of malaria parasites is very clear, namely Image 1 and image 5 with a pattern of malaria parasites is very clear
Platform Digital and Content Innovation to Increase Youth Interest in the Agricultural Sector
No full textThe use of digital technology is essential in increasing the younger generation's interest in the agricultural sector. Deficient awareness of youth in the agricultural sector, even though the agricultural sector has great potential and has a crucial role in handling anything. The methodology carried out in this study uses data collection, initial processing of data, analysis using python, evaluation, and validation of results. Content with agricultural topics, the use of the Internet of things on agriculture that contains the content of the role of the younger generation in the agricultural sector is then used as a dataset. Variables analyzed in these contents include the year of content creation, how many subscribers, number of viewers, and number of videos. In-person interviews with the younger generation were also conducted to explore information with variables in knowledge levels, family environment factors, land availability, social practice, risk factors, and income. The results and discussions of the analysis of content related to agriculture and the Internet of things showed the younger generation's interest in farming with the help of digital platforms. Of the 30 respondents used as a sample, prestige social has the highest value compared to other variables with 0,59. The results obtained from the analysis showed that the number of impressions on content related to the younger generation in the agricultural sector reached 248,882,953 impressions, and the number of impressions related to the Internet of Things content was as many as 23. 969 impressions. The use of technology with the digital Youtube platform is an excellent opportunity to give birth to various kinds of innovations by utilizing digital technology to support the sustainability of the agricultural sector in Indonesia
Interdependency and Priority of Critical Infrastructure Information (Case Study: Indonesia Payment System)
No full textThe sturdy and reliable payment system is one of the most important systems in the digitalization era, especially in the pandemic COVID-19 period. As part of Critical Infrastructure Information (CII), a strategy to protect the payment system is needed to reduce risks that may arise. But the author's best knowledge, in Indonesia, no reference describes the interdependency of the CII sector that could be used as input on strategy making for reducing the risk on all CII sectors which are influencing the payment system. This research uses the Fuzzy-based DANP (FDANP) Framework based on a multi-expert perspective on inter-sector influences to identify the interdependency and priority of the CII sector with a case study on the payment system. The contribution of this research is to provide information about the interdependency and priority of the CII sector. The findings of this research show that 5 sectors that have an influence on other sectors with a case study of the payment system and the information and communication technology sector, the energy and mineral resources sector, and the financial sector are the three major sectors that must be paid more attention to because they have an impact on many sectors.
The sturdy and reliable payment system is one of the most important systems in the digitalization era, especially in the pandemic COVID-19 period. As part of Critical Infrastructure Information (CII), a strategy to protect the payment system is needed to reduce risks that may arise. But the author's best knowledge, in Indonesia, no reference describes the interdependency of the CII sector that could be used as input on strategy making for reducing the risk on all CII sectors which are influencing the payment system. This research uses the Fuzzy-based DANP (FDANP) Framework based on a multi-expert perspective on inter-sector influences to identify the interdependency and priority of the CII sector with a case study on the payment system. The contribution of this research is to provide information about the interdependency and priority of the CII sector. The findings of this research show that 5 sectors that have an influence on other sectors with a case study of the payment system and the information and communication technology sector, the energy and mineral resources sector, and the financial sector are the three major sectors that must be paid more attention to because they have an impact on many sectors
Implementation of Naïve Bayes for Fish Freshness Identification Based on Image Processing
Get PDFConsumption of fish as a food requirement for the fulfillment of community nutrition is increasing. This was followed by an increase in the amount of fish caught that were sold at fish markets. Market managers must be concerned about the dispersion of huge amounts of fish in the market in order to determine the freshness of the fish before it reaches the hands of consumers. So far, market managers have relied on traditional ways to determine the freshness of fish in circulation. The issue is that traditional solutions, such as the use expert assessment, demand a human physique that quickly experiences fatigue. Technological developments can be a solution to these problems, such as utilizing image processing techniques classification method. Image processing with the use of color features is an effective method to determine the freshness of fish. The classification method used in this research is the Naive Bayes method. This study aims to identify the freshness of fish based on digital images and determine the performance level of the method. The identification process uses the RGB color value feature of fisheye images. The stages of fish freshness identification include cropping, segmentation, RGB value extraction, training, and testing. The classification data are 210 RGB value of extraction images which are divided into 147 data for training and 63 data for testing. The research data were divided into fresh class, started to rot class, and rotted class. The research shows that the Naive Bayes algorithm can be used in the process of identifying the freshness level of fish based on fisheye images with a test accuracy rate of 79.37%.
Consumption of fish as a food requirement for the fulfillment of community nutrition is increasing. This was followed by an increase in the amount of fish caught that were sold at fish markets. Market managers must be concerned about the dispersion of huge amounts of fish in the market in order to determine the freshness of the fish before it reaches the hands of consumers. So far, market managers have relied on traditional ways to determine the freshness of fish in circulation. The issue is that traditional solutions, such as the use expert assessment, demand a human physique that quickly experiences fatigue. Technological developments can be a solution to these problems, such as utilizing image processing techniques classification method. Image processing with the use of color features is an effective method to determine the freshness of fish. The classification method used in this research is the Naive Bayes method. This study aims to identify the freshness of fish based on digital images and determine the performance level of the method. The identification process uses the RGB color value feature of fisheye images. The stages of fish freshness identification include cropping, segmentation, RGB value extraction, training, and testing. The classification data are 210 RGB value of extraction images which are divided into 147 data for training and 63 data for testing. The research data were divided into fresh class, started to rot class, and rotted class. The research shows that the Naive Bayes algorithm can be used in the process of identifying the freshness level of fish based on fisheye images with a test accuracy rate of 79.37%
Texture Feature Extraction in Grape Image Classification Using K-Nearest Neighbor
Get PDFIndonesian Grapes are a vine. This fruit is often found in markets, shops, and the roadside. Along with the development of computer technology today, computers can solve problems by classifying objects and objects. How to apply GLCM and K-NN methods for the classification of grapes. The purpose of this study is to apply the GLCM and K-NN methods in the classification of grapes. The dataset used from kaggle.com sources, the data tested are 3 types of grapes, and the number of images is 2624. The fruit that will be used for the data collection and classification process is limited to three types of grapes, namely grape blue, grape pink, and grape white. How to apply GLCM and K-NN methods for the classification of grapes. The feature extraction of GLCM used in this study is the feature contrast, energy, correlation, and homogeneity. From testing the test data, the highest accuracy value is 99.5441% with k = 2 at level 8, while the lowest accuracy value is 24.924% at each k level 2. The GLCM level value is very influential on the accuracy results, namely, the higher the GLCM level value, the higher the GLCM value. accuracy is getting better.Indonesian Grapes are a vine. This fruit is often found in markets, shops, roadside. Along with the development of computer technology today, computers can solve problems by classifying objects and objects. How to apply GLCM and K-NN methods for classification of grapes. The purpose of this study is to apply the GLCM and K-NN methods in the classification of grapes. The dataset used from kaggle.com sources, the data tested are 3 types of grapes, the number of images is 2624. The fruit that will be used for data collection and classification process is limited to three types of grapes, namely grape blue, grape pink and grape white. How to apply GLCM and K-NN methods for classification of grapes. The feature extraction of GLCM used in this study is the feature contrast, energy, correlation, and homogeneity. From testing the test data, the highest accuracy value is 99.5441% with k = 2 at level 8, while the lowest accuracy value is 24.924% at each k level 2. The GLCM level value is very influential on the accuracy results, namely the higher the GLCM level value, the higher the GLCM value. accuracy is getting better
K-Means Clustering Algorithm Approach in Clustering Data on Cocoa Production Results in the Sumatra Region
No full textCocoa agricultural production in Indonesia is currently very low while demand continues to increase every year, so it is very important to build a model that can categorize cocoa farming data. The main objective of this research is to analyze agricultural data using data mining techniques that specifically use the K-Means Clustering algorithm, and Gaussian Mixture Models. In this research, we used quantitative research because it measure number-based data. The results of cocoa production so far still depend on land area, then the number of cocoa trees has a significant effect on the amount of production so it is very important for the government and researchers to develop technologies that can increase cocoa production yields where the demand for cocoa is currently very high in demand worldwide because it can classify the cocoa quality from good quality to poor quality. Based on testing the K-Means Clustering and Gaussian Mixture Model algorithms on data on cocoa production in four provinces, namely North Sumatra, West Sumatra, Lampung and Aceh which were optimized by the Silhouette method, it produced cluster values of 2, 3 and 4. second with a value of 59.8%.
Cocoa agricultural production in Indonesia is currently very low while demand continues to increase every year, so it is very important to build a model that can categorize cocoa farming data. The main objective of this research is to analyze agricultural data using data mining techniques that specifically use the K-Means Clustering algorithm, and Gaussian Mixture Models. In this research, we used quantitative research because it measure number-based data. The results of cocoa production so far still depend on land area, then the number of cocoa trees has a significant effect on the amount of production so it is very important for the government and researchers to develop technologies that can increase cocoa production yields where the demand for cocoa is currently very high in demand worldwide because it can classify the cocoa quality from good quality to poor quality. Based on testing the K-Means Clustering and Gaussian Mixture Model algorithms on data on cocoa production in four provinces, namely North Sumatra, West Sumatra, Lampung and Aceh which were optimized by the Silhouette method, it produced cluster values of 2, 3 and 4. second with a value of 59.8%
UI/UX Analysis and Design Development of Less-ON Digital Startup Prototype by Using Lean UX
Get PDFThe growth of startups in Indonesia continues to experience upward growth. Behind the growth that continues to move up, there is a success rate statistic which is a contradiction behind its development. The startup statistics show that about 90% of startups fail. As many as 75% of unicorn startups believe that a good UI/UX design can increase startup valuations and additional investors' funds. User Interface (UI) and User Experience (UX) are closely related because UX results from UI interactions. Less-On is a provider of private tutoring service providers who serve as an intermediary bridge between teachers and students. This research will be carried out by integrating the processes in the Lean UX method into every process that exists at the stages of software engineering development. The results obtained from this study are a final prototype validated in terms of criticism and suggestions through a questionnaire as a form of Less-On branding. Positive UX and better usability are significant for further development of the prototype private tutor booking application, which plays a vital role in acceptance, satisfaction and efficiency in using this Less-ON application. The UI has good usability for users, with a SUS scoring earn 85.53, which is above average and acceptable.
The growth of startups in Indonesia continues to experience upward growth. Behind the growth that continues to move up, there is a success rate statistic which is a contradiction behind its development. The startup statistics show that about 90% of startups fail. As many as 75% of unicorn startups believe that a good UI/UX design can increase startup valuations and additional investors' funds. User Interface (UI) and User Experience (UX) are closely related because UX results from UI interactions. Less-On is a provider of private tutoring service providers who serve as an intermediary bridge between teachers and students. This research will be carried out by integrating the processes in the Lean UX method into every process that exists at the stages of software engineering development. The results obtained from this study are a final prototype validated in terms of criticism and suggestions through a questionnaire as a form of Less-On branding. Positive UX and better usability are significant for further development of the prototype private tutor booking application, which plays a vital role in acceptance, satisfaction and efficiency in using this Less-ON application. The UI has good usability for users, with a SUS scoring earn 85.53, which is above average and acceptable
Analysis of Public Sentiment Towards Goverment Efforts to Break the Chain of Covid-19 Transmission in Indonesia Using CNN and Bidirectional LSTM
No full textCOVID-19 is a new disease that has a negatively impacts in Indonesia, so the government is taking several measures to suppress the spread of COVID-19, such as new normal, social distancing, health protocols fines, and COVID-19 vaccination. The government's handling efforts have reaped a variety of negative to positive responses from the public on social media, so this study aims to determine the effectiveness of the government's efforts by analyzing public sentiment using the Deep Learning method with 1,875 training datasets consisting of four types government efforts and taken from various media social. The use of Deep Learning begins with testing several Deep Learning architectures to determine the best architecture for predicting data. The architectures tested include CNN and Bi-LSTM, where from these tests, Bi-LSTM outperforms CNN with the best performance achieving the accuracy of 97.34% and 97.33% for precision, recall, and F1-score. The results of public sentiment analysis show that social distancing efforts are considered the most effective by obtaining the most positive sentiments by 33.93%, while the effort to health protocol fines is considered lacking because it obtains the most negative sentiment of 35.64%, so the government must continue to enforce social distancing and optimize other efforts that are still considered ineffective.
COVID-19 is a new disease that has a negatively impacts in Indonesia, so the government is taking several measures to suppress the spread of COVID-19, such as new normal, social distancing, health protocols fines, and COVID-19 vaccination. The government's handling efforts have reaped a variety of negative to positive responses from the public on social media, so this study aims to determine the effectiveness of the government's efforts by analyzing public sentiment using the Deep Learning method with 1,875 training datasets consisting of four types government efforts and taken from various media social. The use of Deep Learning begins with testing several Deep Learning architectures to determine the best architecture for predicting data. The architectures tested include CNN and Bi-LSTM, where from these tests, Bi-LSTM outperforms CNN with the best performance achieving the accuracy of 97.34% and 97.33% for precision, recall, and F1-score. The results of public sentiment analysis show that social distancing efforts are considered the most effective by obtaining the most positive sentiments by 33.93%, while the effort to health protocol fines is considered lacking because it obtains the most negative sentiment of 35.64%, so the government must continue to enforce social distancing and optimize other efforts that are still considered ineffective