Jurnal ELTIKOM
Not a member yet
154 research outputs found
Sort by
Segmentasi Pelanggan Berdasarkan Tingkat Loyalitas Menggunakan K-Means dan Seleksi Fitur LRFM pada Toko Online Retail
No full textCustomer experience is a key component in increasing sales numbers. Customers are important assets that must be kept up for a corporation or firm. Prioritizing customer service is one way to protect client loyalty. To ensure that service priority is right on target, this research was conducted on groups of consumers who are anticipated to have high business prospects. The 2011 retail online shop sales dataset with 379,980 records and eight char-acteristics was used. The length, recency, frequency, and monetary (LRFM) feature selection approach was used in the study process to select features for further segmentation using the K-Means data mining method to define consumer types. Following the completion of the research, clients were divided into four categories: Premium Loyalty, Inertia Loyalty, Latent Loyalty, and No Loyalty. The correct clustering results are displayed in the vali-dation test using the Silhouette Score Index technique, which yielded a score value of 0.943898. Based on the outcomes of this segmentation, business actors may prioritize providing clients with the proper service.Faktor besar dalam meningkatkan angka penjualan adalah pengalaman pelanggan. Pelanggan adalah aset yang berharga untuk bisnis atau perusahaan yang perlu dipertahankan. Pemberian prioritas layanan pelanggan dapat diterapkan sebagai strategi menjaga loyalitas pelanggan. Penelitian ini dilakukan untuk mengelompokan pelanggan yang diperkirakan memiliki prospek yang bagus bagi perusahaan sehingga pemberian prioritas layanan tidak salah sasaran. Data yang digunakan adalah 379980 data dari dataset penjualan toko online retail pada tahun 2011 yang berisi delapan atribut. Proses segmentasi dilakukan dengan metode data mining menggunakan K-Means dan metode feature selection LRFM. Penelitian yang dilakukan menghasilkan pengelompokan pelanggan menjadi empat kategori Premium Loyalty, Inertia Loyality, Laten Loyality dan Tanpa Loyalitas. Dari uji validasi yang dilakukan menggunakan metode Silhoutte Score Index menunjukan hasil clusterisasi yang tepat dengan nilai score 0,943898
PENINGKATAN KEAMANAN DATA END-TO-END SMART DOOR MENGGUNAKAN ADVANCED ENCRYPTION STANDARD
Full text linkSmart Home is one form of implementation of Internet of Things technology in the form of smart homes that can carry out management, monitoring, even reporting. In addition, smart homes can be equipped with security equipment such as Smart Door that can open or lock the door automatically when recognizing the homeowner\u27s face. However, the current Smart Door model has a disadvantage where the stored data on the server and the device are not secured end-to-end. The homeowners\u27 image data on the device is not encrypted with a specific algorithm and validation. Thus, the outside parties can use this high-risk problem to enter the house unnoticed. They disguised themselves as the homeowner by entering false data on the device. Based on this problem, this study has a purpose to increase the model\u27s end-to-end security by implementing the Advanced Encryption Standard algorithm. In addition to increase the security level, the Truncated Decimal-converted SHA-1 checksum validation is added to prevent modifications in each image data. From the results of the model comparison experiment, there was an increase in device resource needs as much as 0.81% increase in process time; 18% CPU usage; 5.3% data usage; and 5.04% for the use of the entire process of memory. But the increase in performance needs is not comparable to the security features presented by the Advanced Encryption Standard algorithm in securing data and servers. So that with improvisation this security is expected to improve the data security of homeowners from outside parties.Smart Home merupakan salah satu bentuk implementasi teknologi Internet of Things dalam bentuk rumah cerdas yang dapat melalukan manajemen, pemantauan, bahkan pelaporan. Selain itu rumah cerdas dapat dilengkapi dengan peralatan keamanan seperti smart door yang dapat membuka maupun mengunci pintu secara otomatis ketika mengenali wajah pemilik rumah. Namun model smart door ini memiliki kelemahan yang di mana data yang tersimpan di dalam server maupun perangkat tidak diamankan secara end-to-end. Perangkat yang menyimpan data-data gambar pemilik rumah tidak dienkripsi dengan algoritma tertentu maupun validasi keaslian data gambar. Sehingga masalah ini dapat dimanfaatkan pihak luar dengan melakukan masquerading atau menyamar dengan cara memasukkan data palsu di dalam perangkat. Berdasarkan masalah yang sudah dideskripsikan, penelitian ini memiliki tujuan untuk meningkatkan keamanan data end-to-end model dengan algoritma Advanced Encryption Standard. Selain itu, penelitian ini juga melengkapi tingkat keamanan dengan validasi integritas data terenkripsi menggunakan teknik Truncated Decimal-converted SHA-1 Checksum untuk membuat nilai hash unik yang dapat mencegah modifikasi di masing-masing data gambar. Dari hasil eksperimen perbandingan model yang dilakukan, terjadi kenaikan kebutuhan sumber daya perangkat sebanyak 0,81% peningkatan waktu proses, 18% penggunaan CPU, 5,3% penggunaan data, dan 5,04% untuk penggunaan memori seluruh proses. Namun peningkatan kebutuhan kinerja ini tidak sebanding dengan fitur keamanan yang dihadirkan oleh algoritma Advanced Encryption Standard dalam mengamankan data perangkat dan server. Sehingga dengan improvisasi keamanan ini diharapkan dapat meningkatkan keamanan data pemilik rumah dari pihak luar
Internet of Thing Menggunakan Firebase dan Nodemcu untuk Helm Pintar
Full text linkThe Indonesian government has made laws with the aim of safety in riding, but some people still violate it, especially in wearing standard helmets and riding tired or drowsy. This needs to be campaigned for public awareness. One of the technology trends in the industrial era 4.0 is the Internet of Things (IoT). This article discuss the utilize of IoT innovation to support riders\u27 safety in preventive efforts by designing a smart helmet prototype. This helmet has the intelligence to force the rider to wear the helmet correctly (helmet detection) and alert the rider when drowsiness (drowsiness detection). This study uses an experimental method, applying the Firebase and NodeMCU platforms to present the IoT concept in implementing the smart helmet functionality. The MPU6050 accelerometer is used for drowsiness detection and for helmet detection using a flex sensor with a switch to ensure that the helmet belt is worn properly. The actuator of the helmet detection is a relay (contact to the engine motor), while the drowsiness detection actuator is the buzzer (beep sound). The two smart helmet functionalities run well. The accuracy value for drowsiness detection is 78% and for helmet detection 100%
Ekstraksi Fitur Tekstur dan Warna pada Kulit Katak Menggunakan GLCM dan Momen Warna
Full text linkAnura is an order in the Amphibian class consisting of frogs and toads. Anura is very important in the ecosystem, especially its role as part of the food chain. Anura\u27s main role is to maintain the balance of the ecosystem and as a bioindicator agent for changing environmental conditions such as water pollution, habitat destruction, disease and parasites, and climate change. This research applies digital image processing technology which is expected to assist in detecting types of frogs based on color and texture. This research uses 5 types of frogs, namely kongkang gading, kongkang poison, striped trees, small trees and flying trees with 20 images of each type of frog. This research uses the color feature extraction methods such Color Moment and texture extraction GLCM (Gray Level Co-occurance Matrix), then classified using K-Star. The results of the K-Star performance evaluation to classify the 5 types of frogs obtained the Accuracy (Acc) value of 0.93, Precision (Prec) of 0.94, Recall (Rec) of 0.93 and F-measure of 0.93. So that the classification results of frog species on texture and color feature extraction using the GLCM method and the Color Moment with the K-Star classification method have high performance and can work well
Model Sistem Pengendalian Suhu dan Kelembaban Ruangan Produksi Obat Berbasis NodeMCU ESP32
Full text linkProduction process in a pharmaceutical industry must follow the guidelines stated in Current Good Manufacturing Practice (CGMP). The production process has to be stopped if the temperature and the humidity of the production room do not meet the set point and a report about the caused has to be made. This research proposed a model of a temperature and humidity automatic control system based on Node MCU ESP32 and give the information to technicians continuously. With the php MyAdmin Web Server connection, data of temperature and humidity can be stored and monitored remotely using a smartphone or a computer. A DHT 11 sensor is used to detect temperature and humidity, a Peltier fan is used to control the room temperature and a dehumidifier is used to control the air humidity. The system controls C and D production class room according to CGMP for liquid drug type in a sterile room. The C class drug production room temperature range is set from 16ΓΕ‘C to 25ΓΕ‘C and the air humidity range is 45% to 55%. The D class drug production room temperature range is set 20ΓΕ‘C to 27ΓΕ‘C and the air humidity range is 40% to 60%. From the test results, it can be seen that the system can control room temperature and humidity automatically when there are disturbances as well as recording the time when the disturbances occur to complete the data reports during the drug production process
IOT Application For Conveyor Motor Load Current And Temperature Monitoring Device for Factory Acceptance Test in Industrial Application
Full text linkIn industrial application on machine manufacturer multinational company, especially on the conveyor manufacturing company, before delivering the conveyor to overseas customer, there are some regulations need to be complied to ensure the product quality is always good. The system to ensure the product quality before delivery is named by Factory Acceptance Test (FAT). The purpose of doing this is to gain the trust and satisfaction of the buyer company by ensuring the quality before delivery. To ensure the product quality, this device was designed following the customer check sheet and requirement by giving them reliable data of the load current on each line of the motor and the motor temperature. This device is consisting of WEMOS D1 mini as the main controller and an IoT device, thermocouple type K as a temperature sensor, MAX6675 as the driver of the thermocouple, SCT-013-005 as a split-core current sensor, Arduino Nano as the second controller, and LCD 2004 as a real-time display. The IoT Application for Conveyor Motor Load Current and Temperature Monitoring Device is successfully created with the output is a table of data and the line chart which consists of Load current on each phase (U1, V1, W1), the motor temperature, and the limitation of each data so the user is easier to determine the commissioning result of the Factory Acceptance Test
SISTEM KONTROL SUDUT PITCH BILAH TURBIN ANGIN MENGGUNAKAN LOGIKA FUZZY UNTUK VARIABLE SPEED VERTICAL AXIS WIND TURBINE (VAWT)
Full text linkVAWT (Vertical Axis Wind Turbine) is a turbine that has an upright mechanical structure with its blades rotating toward a perpendicular z-axis. Based on the experimental results, it is found that there is a relationship between the rotational speed of turbine that rotates generator with the output voltage and power. Thus, it is necessary to control the wind turbine speed so it can rotate according to the set point to be achieved. The contribution of this research is the development of a Fuzzy logic-based control system to control the speed of VAWT turbine where the speed of turbine is used as feedback. To design a Fuzzy rule base, the characteristics of the wind turbineΓ’β¬β’s response to wind speed are investigated first. Then Fuzzy logic-based controller is created and implemented. To test the effectiveness of the Fuzzy controller made, the implementation is carried out on a VAWT turbine while the simulation is applied to PMSG model using wind turbine through Simulink/Matlab. Based on simulation and experiment results, the performance of the control system using Integral Absolute Error (IAE) for each turbine speed set point value (35, 45, 85, and 100 RPM), it is found that for a small set point value, the IAE value will be larger than higher setpoints. The percentage of the average IAE value for the simulation is 10.25% higher than the experiment. It further shows that the control turbine speed at low speeds is relatively more difficult than at higher speeds.Turbin angin sumbu vertikal atau VAWT (Vertical Axis Wind Turbine) merupakan turbin angin yang memiliki struktur mekanik tegak ke atas dengan bilah-bilah turbin yang berputar terhadap sumbu-z tegak lurus. Berdasark an hasil eksperimen diperoleh bahwa terdapat hubungan antara kecepatan putaran turbin yang memutar generator dengan keluaran tegangan dan daya yang dihasilkan, sehingga diperlukan upaya mengendalikan kecepatan turbin angin agar dapat berputar sesuai setpoin yang ingin dicapai. Kontribusi dari penelitian ini berupa pengembangan sistem kontrol berbasis logika Fuzzy untuk mengendalikan kecepatan turbin VAWT dengan hanya menggunakan umpan balik berupa kecepatan turbin angin. Hal ini berbeda dengan penelitian sebelumnya dimana kecepatan angin dan keluaran daya dijadikan sebagai umpan balik. Untuk mengetahui karakteristik dari kecepatan turbin dan keluaran tegangan, serta hubungan antara kecepatan turbin dan kecepatan angin dengan variasi sudut pitch bilah, maka pengujian dilakukan dalam skala laboratorium dengan menggunakan blower. Untuk merancang rule base (aturan) Fuzzy, maka karakteristik dari respon turbin angin terhadap kecepatan angin diteliti terlebih dahulu. Kemudian kontroller berbasis logika Fuzzy dibuat dan diimplementasikan. Untuk menguji efektivitas kontroller Fuzzy yang dibuat, maka implementasi dilakukan pada turbin VAWT sedangkan simulasi diterapkan pada model PMSG turbin angin melalui Simulink/Matlab. Berdasarkan hasil pengujian melalui simulasi dan eksperimen dengan mengukur kinerja respon sistem kontrol menggunakan Integral Absolut Error (IAE) untuk masing-masing nilai setpoin kecepatan turbin (35, 45, 85, dan 100 RPM) diperoleh bahwa untuk nilai setpoin kecil maka nilai IAE akan semakin besar dibandingkan setpoin yang lebih tinggi. Persentase nilai rata-rata IAE untuk simulasi adalah 10,25% lebih tinggi dibandingkan dengan eksperimen. Hal ini kemudian menunjukkan bahwa pengendalian kecepatan turbin pada kecepatan rendah relatif lebih sulit dibandingkan dengan kecepatan turbin lebih tinggi
Komparasi Performansi Antara Proportional Integral Derivative Controller (PID) Dan Fuzzy Logic Controller (FLC) Pada Penjejak Cahaya Dengan Tiga Sensor
Full text linkThe technology of light tracking monitors the solar panels to track the sun with full efficiency, and the solar panels can be upright to the sunlight in order to maximize the absorption of solar energy, so this system has a higher efficiency than non-tracking systems. This study aimed to obtain a controller that works accurately between the Proportional, Integral, and Derivative Controller (PID) and the Fuzzy Logic Controller (FLC) Algorithm by comparing the performance of the two algorithms in regulating the direction of the light tracker to detect the presence of sunlight. This solar prototype uses nine lamps as a simulation to determine the accuracy and precision of the angles of the two light trackers. The parameters compared in this test were the aspects of angular velocity and angle accuracy. The mean value of angular velocity obtained from the PID light tracking test results was 0.16 rad/s and the average linear velocity was 0.092 m/s whereas in the FLC light tracker, the average angular velocity value was 0.207 rad/s. Tests using a PID light tracker resulted in an X-axis accuracy of 45% and a Y-axis accuracy of 30%. The FLC light tracker, on the other hand, had an X-axis accuracy of 80% and a Y-axis accuracy of 30%.The precision value obtained by the PID light tracker on the X axis was 45% and the Y axis was 38%, while the precision value obtained by the FLC light tracker on the X axis was 71% and the Y axis was 33%. Based on the overall calculations, it can be concluded that the FLC light tracker has an increase in the speed value of 29% and an increase in the value of accuracy in the accuracy aspect by 35% and the precision aspect by 26% compared to the PID light tracker in previous studies
Finding The Most Desirable Car Using K-Nearest Neighbor From E-Commerce Websites
Full text linkThe increasing number of cars that have been released to the market makes it more difficult for buyer to choose the choice of car that fits with their desired criteria such as transmission, number of kilometers, fuel type, and the year the car was made. The method that is suitable in determining the criteria desired by the community is the K-Nearest Neighbors (KNN). This method is used to find the lowest distance from each data in a car with the criteria desired by the buyer. Euclidean, Manhattan, and Minkowski distance are used for measuring the distance. For supporting the selection of cars, we need an automatic data col-lection method by using web crawling in which the system can retrieve car data from several ecommerce websites. With the construction of the car search system, the system can help the buyer in choosing a car and Euclidean distance has the best accuracy of 94.40%