One of the essential factors in the cultivation of freshwater ornamental fish in the aquarium is the water quality. Quality aquarium water is clear water with appropriate temperature and pH. In this ...study, the design and implementation of the control system based on fuzzy logic for filter pump work cycle were reported. The fuzzy logic in the controller will provide the strength of filter pump work based on the information on the turbidity level of water obtained from the photodiode sensor and the acidity of the water collected from the pH sensor. The results of the fuzzy logic controller design are implemented in Arduino UNO R3 microcontroller to control filter pump strength. The experimental results show that the controller can improve the water clarity level at the desired level in a reasonably short time. In addition, it was also demonstrated that the system performance was still good even in the existence of disturbance.
ABSTRAKPengenalan gerakan tangan dianggap sebagai bagian penting dari interaksi manusia komputer, memungkinkan komputer untuk mengenali dan menafsirkan gerakan tangan dan menjalankan perintah. ...Penggunaan machine learning dimanfaatkan untuk mencari tren dan pola yang berbeda. Namun, tantangan untuk menerapkan machine learning menjadi bagaimana memilih di antara berbagai model berbeda digunakan untuk kumpulan data atau kasus berbeda. Tujuan dari penelitian ini adalah mengukur kinerja model machine learning yang diusulkan dengan pemilihan hyperparameter yang sesuai dalam mengenali 10 pola angka berdasarkan gerakan tangan di udara. Dalam makalah ini, model KNN, SVM, dan ANN-PSO diusulkan. Eksperimen dilakukan dengan mengumpulkan data gerakan yang berasal dari MPU-6050. Kinerja metode yang diusulkan dievaluasi menggunakan metrik standar seperti akurasi klasifikasi, presisi, recall, f1-score, dan AUC-ROC. Hasilnya menunjukkan bahwa akurasi rata-rata mencapai 87%.Kata kunci: HCI, hand gesture recognition, machine learning, MPU-6050, pola ABSTRACTHand gesture recognition is considered an essential part of human-computer interaction (HCI), enabling computers to recognize and interpret hand gesturesand execute commands. The use of machine learning is utilized to look for different trends and patterns. However, the challenge for implementing machine learning becomes how to choose between different models used for different datasets or cases. This research aims to measure the performance of the proposed machine learning model by selecting the appropriate hyperparameters in recognizing 10 number patterns based on hand gestures in the air. In this paper, KNN, SVM, and ANN-PSO models are proposed. Experiments were carried by collecting gesture data from MPU-6050. The performance of the proposed method was evaluated using standard metrics such as classification accuracy, precision, recall, f1-score, and AUC-ROC. The results show that the average accuracy reaches 87%.Keywords: HCI, hand gesture recognition, machine learning, MPU-6050, pattern
Abstract
Based on the structure and dynamic process of the ladder secondary double-sided linear induction motor (DSLIM) with asymmetry position of primary part of motor, the motor parameters may ...change with the secondary position, which directly cause the stability of electromagnetic thrust. It is difficult to meet the system control performances for designing of controller in the dynamic characteristics of the speed closed loop. This paper describes some solving algorithm by adopting the rotor field oriented control as the model matching strategy to achieve the smooth control of the electromagnetic thrust. The arrangement of model matching process is based on the Nevallina pick solution as linear interpolation method. Through the robust control concept and model matching control, the stability of the electromagnetic thrust during the motor step change process can be achieved. The simulation results verify the truth of the presented control strategies.
In this paper, the efficiency of photovoltaic panels is improved by adding a sun tracking system. The solar tracking system is used for tracking the sun so that photovoltaic always faces the sun. ...This system uses a dual axis consisting of horizontal rotation axis and a vertical rotation axis. The horizontal rotational axis motion is to follow the azimuth angle of the sun from north to south. Then, to follow the sun's azimuth angle from east to west is the vertical axis motion. Both types of movements are controlled using a PID controller that is optimized with an artificial intelligence approach, namely particle swarm optimization (PID-PSO), firefly algorithm (PID-FA), imperialist competitive algorithm (PID-ICA), bat algorithm (PID-BA), and ant colony optimization (PID-ACO). Experiments of various approaches were carried out and the corresponding performance compared. The experimental results show that PID-BA performs best in terms of settling time and overshoot. The results also allow the comparison of different PID controller and the calculation of the fastest completion time.
ABSTRAKKendali formasi adalah topik penelitian kendali multi-robot, dimana sekelompok robot dapat mencapai formasi tertentu dan mempertahankannya ketika berpindah ke arah yang diinginkan. Salah satu ...pengembangan kendali formasi adalah kendali formasi berdasarkan jarak dimana setiap individu robot menggunakan informasi jarak antara sesamanya untuk mencapai tujuan formasi. Banyak pengembangan yang dilakukan pada kendali formasi berdasarkan jarak menggunakan model yang sederhana dan membutuhkan pengembangan lebih lanjut untuk penerapan kendali ke model yang lebih nyata. Ketika penerapan kendali formasi berdasarkan jarak, terdapat permasalahan kondisi awal yaitu robot tidak dapat menentukan koordinat tetangganya. Penelitian ini akan mengembangkan algoritma cosinus sebagai solusi untuk kondisi awal kendali formasi berdasarkan jarak. Algoritma cosinus terinspirasi dari rumus segitiga sederhana dan mengharuskan robot melakukan dua langkah saja untuk dapat menemukan koordinat tetangganya. Hasil percobaan simulasi, kendali formasi berdasarkan jarak menggunakan tiga model robot holonomic dan penerapan algoritma cosinus membutuhkan waktu rata-rata 6.5 detik untuk menemukan koordinat tetangganya.Kata kunci: Kendali Formasi, Multi-Robot, Algoritma Cosinus, Mobile Robot. ABSTRACTFormation control is a research topic of multi-robot control, where a group of robots can reach a certain formation and defend it when moving in the desired direction. One of the developments is distance-based where formation goals achieved using the distance between each other only. Many developments are using a simple model and need further development into a realistic model. When applying distance-based, there is a problem in the initial condition, namely that the robot cannot find the coordinates of its neighbors when using only distance. In this work, the cosine algorithm was developed as a solution to the initial conditions which are inspired by a simple triangle formula and need only two steps to find the coordinates. From simulation experiment results, distance-based formation control using three holonomic robot models and the application of the cosine algorithm takes an average of 6.5 seconds to find the coordinates of its neighbors.Keywords: Formation Control, Multi-robot, Cosine Algorithm, Mobile Robot.
The optimal performance of solar panels is very important to produce maximum electrical energy. Solar panels can work optimally when equipped with a solar tracker. The solar panel tracker works by ...following the sun's movement. A Proportional, Integral, Derivative (PID) based control is used to optimize the performance of the solar tracker. An optimal tuning is needed to get the PID parameter. The Firefly method is an intelligent method that can be used to optimize PID parameters. Three Firefly Algorithm (FA) parameters are used in the program: Beta is used to determine firefly speed, Alpha is used for flexibility of movement, and Gamma is used for more complex constraints or problems. This Dual Axis photovoltaic tracking study uses the beta value determination, changing the Bêta value from 0.1 to 0.9. From the results of 10 models, it was found that the PID constant values were varied. On the horizontal Axis, the best results are if the Beta is given at 0.4, and the worst result is if the Beta is given at 0.8. On the vertical Axis, the best results are if the Beta is given at 0.3, and the worst result is if the Beta is given at 0.8.
Abstract
The Firefly Algorithm (FA) method is presented inspired by the social behavior of fireflies and the phenomenon of bioluminescent communication. There are three FA parameters used in the ...program, beta is used to determine firefly speed, alpha is used for flexibility of movement, and gamma is used for more complex constraints or problems. In this dual axis photovoltaic tracking study using the beta value determination. By changing the Bêta value from 0.1 to 0.9. From the results of 10 models, it was found that the PID constant values were varied. On the horizontal axis, the best results if the beta is given at 0.4 and the worst result if the beta is given at 0.8. On the vertical axis, the best results if the beta is given at 0.3 and the worst result if the beta is given at 0.8.
Post-disaster sector damage data is data that has features or criteria in each case the level of damage to the post-natural disaster sector data. These criteria data are building conditions, building ...structures, building physicals, building functions, and other supporting conditions. Data on the level of damage to the post-natural disaster sector used in this study amounted to 216 data, each of which has 5 criteria for damage to the post-natural disaster sector. Then the 216 post-disaster sector damage data were processed using Principal Component Analysis (PCA) to look for labels in each data. The results of these labels will be used to cluster data based on the value scale of the results of data normalization in the PCA process. In the data normalization process at PCA, the data is divided into 2 components, namely PC1 and PC2. Each component has a variance ratio and eigenvalue generated in the PCA process. For PC1 it has a variance ratio of 85.17% and an eigenvalue of 4.28%, while PC2 has a variance ratio of 9.36% and an eigenvalue of 0.47%. The results of the data normalization are then made into a 2-dimensional graph to see the visualization of the PCA results data. The result is that there is 3 data cluster using a value scale based on the PCA results chart. The coordinate value (n) of each cluster is cluster 1 (n<0), cluster 2 (0 ≤n <2), and cluster 3 (n≥2). To test these 3 groups of data, it is necessary to conduct trials by comparing the original target data, there are two experiments, namely testing the PC1 results with the original target data, and the PC2 results with the original target data. The result is that there are 2 updates, the first is that the distribution of PC1 data is very good in grouping the data when comparing the distribution of data with PC2, because the variance ratio and eigenvalue values of PC1 are greater than PC2. While second, the results of testing the PC1 data with the original target data produce good data grouping, because the original target data which has a value of 1 (slightly damaged) occupies the coordinates of cluster 1 (n<0), while the original target data which has a value of 2 (damaged moderately) occupies cluster 2 coordinates (0 ≤n <2), and for the original target data the value 3 (heavily damaged) occupies cluster 3 coordinates (n≥2). Therefore, it can be concluded that PCA, which so far has been used by many studies as feature reduction, this study uses PCA for labeling unsupervised data so that it has an appropriate data label for further processing.
IOT Based Climate Monitoring System Muslim, Muhammad Aziz; Setyawan, Raden Arief; Basuki, Achmad ...
IOP Conference Series: Earth and Environmental Science,
04/2021, Letnik:
746, Številka:
1
Journal Article
Recenzirano
Odprti dostop
Abstract
In this paper, an IOT based climate monitoring system for rural area is proposed. The selected location for IOT sensor placement is Sumberbrantas village which is vulnerable for flood, ...landslide and strong wind disasters. For these reasons wind behaviors, rainfall and temperature sensors are installed in IOT stations. Based on information from local residents, strong winds always blow every year. The wind flowed for several days causing residents to be unable to move outside their homes. This wind is flowing so fast that it can damage the roof of the house. However, currently there is still no device that accurately measures changes in air pressure or wind speed in the area. To collect data, as well as to anticipate problems caused by these strong winds, an IOT-based monitoring system was built to observe the weather that occurred in the area. Experiments show that the proposed monitoring system is able to send monitoring data every 5 minutes. The monitoring data consist of temperature, humidity, wind direction, wind speed, barometric pressure and rainfall.