Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control
Not a member yet
424 research outputs found
Sort by
Game Development of “Kwace Adat Bali” for The Socialization of Balinese Traditional Dress-Up Ethics
Get PDFMany young people have begun to violate the ethics of Balinese traditional dress up by using strict lacy blouse (kebaya), high split sarong (kamen), men sarong (kamen) that not taper on the tip and excessive accessories. Game of “Kwace Adat Bali” is expected as a means of socialization in Balinese traditional dress-up ethics appropriately. In this game, the Balinese traditional dress-up style is classified into three types, namely light traditional clothing (payas alit), middle traditional clothing (payas madya), and great traditional clothing (payas agung). The proposed method is Design Game Based-Learning Instructional Design (DGBL-ID) which is combined with a shuffle random algorithm to shuffle game items. The Game of “Kwace Adat Bali” has tested using alpha testing, beta testing, t-test, and game engagement questionnaire (GEQ). The alpha testing result was 100% game functionality has run suitable for the design. Beta testing shows that overall this game got a value of 77% from 65 respondents. There was a significant difference between user knowledge before and after playing the game of “Kwace Adat Bali” as indicated by t table value of 1.997, t value of 6.5, and the critical value of α = 0.05. The proposed method had an engagement rate of 8.7% higher than just using the DGBL-ID method in developing the game. Therefore, it can be concluded that the game feasible is considered as a new means of socialization in Balinese traditional dress up ethics for the younger generation
Mental Disorder Detection via Social Media Mining using Deep Learning
Get PDFDue to the imperceptible nature of mental disorders, diagnosing a patient with a mental disorder is a challenging task. Therefore, detection in people with mental disorders can be done by looking at the symptoms they experience. One symptom in patients with mental disorders is solitude. Patients with mental disorders feel indifferent to their environment and mainly focus on their own thoughts and emotions. Therefore, the patient looks for a place that can accommodate his feelings. Twitter is one of the most widely used media in measuring one's personality through everyday statements. The symptoms as suggested by psychologists can be explored more broadly using Natural Languages Processing. The process involves taking a lexicon containing keywords that could indicate symptoms of depression. This study uses five criteria as a measure of mental health in a statement: sentiment, basic emotions, the use of personal pronouns, absolutist words, and negative words. The results show that the use of sentiments, emotions, and negative words in a statement is very influential in determining the level of depression. A depressed person more often uses negative words that indicate his self-despair, prolonged sadness, even suicidal thoughts (e.g. "sadly”, “scared”, “die”, “suicide”). In the classification process, LSTM Deep Learning generates an accuracy of 70.89%; precision of 50.24%; recall 70.89%
Multi-scale Entropy and Multiclass Fisher’s Linear Discriminant for Emotion Recognition Based on Multimodal Signal
Get PDFEmotion recognition using physiological signals has been a special topic frequently discussed by researchers and practitioners in the past decade. However, the use of SpO2 and Pulse rate signals for emotion recognitionisvery limited and the results still showed low accuracy. It is due to the low complexity of SpO2 and Pulse rate signals characteristics. Therefore, this study proposes a Multiscale Entropy and Multiclass Fisher’s Linear Discriminant Analysis for feature extraction and dimensional reduction of these physiological signals for improving emotion recognition accuracy in elders. In this study, the dimensional reduction process was grouped into three experimental schemes, namely a dimensional reduction using only SpO2 signals, pulse rate signals, and multimodal signals (a combination feature vectors of SpO2 and Pulse rate signals). The three schemes were then classified into three emotion classes (happy, sad, and angry emotions) using Support Vector Machine and Linear Discriminant Analysis Methods. The results showed that Support Vector Machine with the third scheme achieved optimal performance with an accuracy score of 95.24%. This result showed a significant increase of more than 22%from the previous works
The Calorie Burning Calculation System in Jogging Using a Thresholding-Based Accelerometer Sensor
Get PDFJogging has benefits for burning calories as well as for losing the weight of the body. However, the reality that often happens is that sportsmen overwork their body in exercising so that it has passed its normal threshold. This causes over or lower calorie burning in these athletes. To overcome these problems, we need a device that can later monitor calorie burning. This device is created on an Android-based platform using an accelerometer sensor. Using this sensor, the system can count the number of a person’s steps previously obtained through the threshold value as the threshold value to determine the steps. Calculation of calorie burning uses a formula that involves the number of footsteps, time, and weight of the user. This application testing involved 15 participants by comparing the calorie burning results through the application and manual calculation, so that the overall error percentage of 0.60% was obtained, so it can be concluded that 99.40% of the calorie burning calculation system in jogging using a thresholding-based accelerometer sensor is appropriate for athletes to provide information of their calories burning in jogging
The impact of Nodes Distance on Wireless Energy Transfer System
Get PDFWireless energy transfer (WET) reemerges as the method for transmitting electric power without the necessity to deal with cable losses and an aesthetically pleasing environment. The problem with WET is how to maintain magnetic induction as the distance gets further. This paper investigates the impact of nodes distance on the WET system. The experimental results show that the most effective distance among transmitter, nodes, and receiver are 4 cm. The measurement is taken with and without load. The without load application give that for node 1; the results are 6 V, 110 mA, and 2.85 mT for voltage, current, and magnetic flux, respectively. At the application of 2 nodes, the voltage is 6.8 V, the current is 0.124 mA, and the magnetic flux is 3.83 mT, and at three nodes installation, it is 7 V, 134 mA, and 3.83 mT. During the application of 3-Watt and 5-Watt lamp, at 4 cm distance, the power received is 1.66 W and 3.66 W at 3-Watt and 5-Watt lamp for one node, 1.84 W, and 3.84 for two nodes, and 1.93 W and 3.93 for three nodes. The experimental results show that the transmitted signal can be prolonged by installing nodes. Even though this study shows that 4 cm is the most effective, it is possible to increase up to 20 cm to power a 3-Watt lamp and 5-Watt lamp
Soybean Disease Detection with Feature Selection Using Stepwise Regression Algorithm: LVQ vs LVQ2
Get PDFndonesia's soybean needs increase from year to year. But according to data from the Badan Pusat Statistik (BPS) the amount of national soybean productivity is still low, so the fulfillment of soybean needs is done by importing soybeans from several countries such as China, Ukraine, Canada, Malaysia, and the United States. Low soybean productivity is caused by several factors. One of the causes is disease. This study aims to create a soybean disease detection by applying Learning Vector Quantization 2 (LVQ2) neural network algorithm(ANN) and Stepwise Regression Algorithm attribute selection. The attribute variables used consisted of 35 symptoms of the disease in soybean crop data. The data used in this study is a soybean dataset taken from University of California Irvine Machine Learning Repository as much as 200 data. The distribution of training data and test data is done by the k-fold cross validation method with a value of k = 10. The result of the study shows that the best paramater use in lVQ2. The results showed that the best parameters in LVQ2 is learning rate (α) value of 0.3; epsilon 0.04; and maximum epoch 100. While the best attribute selection uses the parameter p to enter and p to remove of 0.15 which produces 17 selected attributes such as date, plant stand, precipitation, leaves, leaf spot halo, leaf spot margins, leafspot size, leaf mildew, stem canker, stem fungi, external decay, fruit pods, fruit spots, seeds, mold growth, seed discolor, roots. The best results in this study resulted in an accuracy of 90.5%, 9.5% error rate, 90.5% sensitivity, and 98.94% specificit
Experimental Study on The Effect of Arches Setting on Semi-Flexible Monocrystalline Solar Panels
Get PDFIndonesia has a high potential for renewable energy, especially solar power, due to its location in the equator and blessed with an abundance of sunlight. However, the energy potential from the sun is not maximally utilized. One of the efforts to increase the generated electricity and efficiency is by applied the panels in arches setting. This setting is made possible by the availability of the semi-flexible monocrystalline solar panel. This paper investigates the increment of harvested power and efficiency by arranging the solar panel in concave, convex, and plane settings. The data were taken in August 2019, where Palembang experiences the dry season and January 2020 during the rainy season. The highest power produced (20.27 Watt) and efficiency (13.14%) were achieved in a concave setting during the dry season. The convex setting produced more power and efficiency (13.26 Watt and 9.30%) compared to the plane setting (10.24 Watt and 9.71%). These results show that arches setting are more efficient to harvest solar power and give more extensive applications such as to power a dynamics mobile robot applied in agriculture
As-RaD System as a Design Model of the Network Automation Configuration System Based on the REST-API and Django Framework
Get PDFThe use of information technology these days are very high. From business through education activities tend to use this technology most of the time. Information technology uses computer networks for integration and management data. To avoid business problems, the number of network devices installed requires a manageable network configuration for easier maintenance. Traditionally, each of network devices has to be manually configured by network administrators. This process takes time and inefficient. Network automation methods exist to overcome the repetitive process. Design model uses a web-based application for maintenance and automates networking tasks. In this research, the network automation system implemented and built a controller application that used REST API (Representational State Transfer Application Programming Interface) architecture and built by Django framework with Python programming language. The design modeled namely As-RaD System. The network devices used in this research are Cisco CSR1000V because it supports REST API communication to manage its network configuration and could be placed on the server either. The As-RaD System provides 75% faster performance than Paramiko and 92% than NAPALM
A Fuzzy Logic-Based Automation toward Intelligent Air Conditioning Systems
Get PDFMost of the energy used in residential buildings originates from air conditioners. Meanwhile, air conditioner manufacturers are addressing this issue by the production of efficient air conditioners. However, the convertible frequency air conditioners are expensive, up to 60% higher than the fixed frequency control air conditioners. Besides the human behavior in determining the temperature, setpoint plays an important role regardless of the air conditioners technology used. This study incorporated intelligence in setting up the temperature by means of specially designed remote control. The Tsukamoto fuzzy reasoning was utilized as a decision making system with two inputs, namely the outdoor temperature and the number of occupants. The device used DHT22 as the temperature sensor and HC-SR04 to detect incoming and outgoing occupants. Furthermore, the fuzzy inference system generated infrared signal associated with the temperature setpoint. This signal was received by the air conditioner receiver to adjust the temperature setpoint accordingly. The result of this study showed that the fuzzy inference system determines the temperature setpoint appropriately under variations of surrounding temperature and the number of occupants. The proposed approach yielded a satisfactory perception of thermal comfort and also a promising approach to energy conservation
Geographic Information System for a Community-Based Water Quality Mapping of Rivers in Indonesia
Get PDFRiver Water with good quality status is the primary needs for the Indonesian people who live along the river. Indonesia has more or less 303 rivers with varied status of water quality. On the other side, the government is obliged to conduct the current situation mapping and to spread the status of river water quality to the surrounding society. It is certainly not an easy job considering the amount and width of the monitoring area. Therefore, this research has proposed a new concept to map the status of river water quality using the STORET method by involving the active participation of the local river community. The locations of research are: Kambaniru river, Brantas river, dan Gajah Wong river. There are seven parameters used to determine the status of river water quality those are: temperature, EC/DHL, TDS, PH, DO, BOD and Caliform. The river community can report the data of analysis result into a system in accordance with the sampling location by enclosing the spatial data. The system will present the status of water quality starting from each point of location to the status of water quality of certain river. The testing result functionally indicates that the system is able to give perfect accuration value. While from its usability, the respondents’ responses are as follows: very agree 60.40%, agree 37.95%, and disagree 1.65%