SHM Publisher Journals
Not a member yet
315 research outputs found
Sort by
Design of ANFIS system to detect the condition of generator set model P22-6 based on Omron CJ1M PLC
Full text linkThe application of machine monitoring systems is currently increasingly needed, one of which is on generators. Generator sets are one of the important elements in providing energy needed in company operations. However, to ensure optimal performance and prevent unexpected engine damage, careful monitoring of the generator set's operational conditions is required, especially of key variables such as temperature, rotation speed, and engine vibration. The purpose of this study is to identify the condition of the generator set using three parameters. In this research, adaptive neuro fuzzy inference system (ANFIS) is used as a tool to model the relationship between inputs (temperature, speed, and vibration) and outputs (engine condition). The dataset for normal conditions amounted to 25 data and for abnormal conditions amounted to 25 data. From this data, an RMSE of 0.000032 was obtained in the 3-3-5 membership function structure with a trapezoidal type membership function. And at the stage of applying fuzzy to the Omron PLC, the RMSE is 0. Simulations are carried out to test the effectiveness of ANFIS in predicting machine conditions based on monitored parameters
Comparison of ethyl acetat fracination of ganitrie (Elaeocarpus sphearicus) seeds as anti bacterial of Staphylococcus aureus and determination of total flavonoid content
No full textInfectious disease is a disease coused by the presence pf pathogenic microbes. Stahpylococcus aureus is a gram positive aerobic bacterium that couses phyogenic infections on humans. Antibiotics are the best choise to treat an infections. The purpose of this study was to determine the antibacterial activity of ganitri seed (Elaeocarpus sphearicus) to determine the exstract ratio, the ethyl acetat fractination of ganitri seeds woth a concetration of 35% on the growth of staphylococcus aureus bacteria and to determine the total flavonoid content. Exctraction was carried out by maceration method for 3x24 hours with 96% ethanol as solvent. Exctraction fractination using 2 methods, the first method is using 30% ethanol, cloroform, and ethyl acetat as solvent. The second fractination method uses hot destiled water and ethyl acetat as solvents. The test result of total flavonoid content in ganitri (Elaeocarpus sphearicus) seeds in ethanol exstract were 38.009 mgEQ / g, fraction 1 of 99.512 mgEQ / g, fraction 2 of 68.235 mgEQ / g. From the result of the determinatoin of the ethyl acrtat fraction 1 had highest yield with an average value of 99,512 mgEQ/g. The antibacterial activity test was 35% in each sample ang using a positive control of ciprofloxcacin and a negative control of DMSO. Based on the result of the clear zone of the ethanol extract was 1.118 cm, the ethyl acetate 1 fraction was 1.170 cm, and the ethyl acetat 2 fraction was 0,956 cm
Classification of residual hearing of deaf students based on audiometer using google data studio visualization method
Full text linkClassification of hearing loss is necessary because it provides treatment or learning methods for students which are certainly not the same. This classification is displayed in a graphical form because graphics are able to provide information quickly. The results of this writing are information in the form of visualization of the residual hearing which is grouped according to the decibels or residual hearing they have. Patterns that will be applied in learning will later be adjusted based on classification, so that students can comfortably follow the learning process. When creating this visualization, use Google Data Studio because it can be used to represent complex data sets in an interesting and clear way. The data used are data on deaf students for 2014-2021, with a total of 357 data and 14 attributes. The results of data processing are in the form of graphs of students for each generation, distribution of student demographics, and classification of student hearing measurement results. From the visualization results, 3 categories were obtained, with the results being 9 light categories,, 129 medium categories and 219 heavy categories. The mild category will receive oral treatment, while the moderate and severe categories will be given sign language and written treatmen
Adaptive deep learning based on FaceNet convolutional neural network for facial expression recognition
Full text linkFacial recognition technology has become increasingly crucial in various applications, from personal identification, security, and human-care. Facial recognition has numerous practical applications, ranging from assessing mental health and well-being through facial expressions to evaluating customer satisfaction in service quality ratings. This study aims to develop a facial recognition model using a Convolutional Neural Network (CNN) with FaceNet architecture. The proposed method utilizes an advanced deep learning approach to generate high-quality facial embeddings, enhancing the model's ability to accurately identify and verify individuals. Our methodology includes training the CNN with FaceNet architecture, achieving an impressive average accuracy of 99.93%, with precision, recall, and F1-score all reaching 100%. The model demonstrated both high accuracy and efficiency, with an average training time of 13 minutes and 51 seconds. Future research should explore incorporating data augmentation, K-fold cross-validation, and additional transfer learning techniques to further enhance model performance and generalization. These advancements could lead to more resilient and flexible facial recognition systems capable of functioning effectively in diverse and challenging real-world conditions
Real-time detection of indonesian sign language (ISL) gestures based on long short-term memory
Full text linkeaf people often encounter communication challenges, and sign language serves as a crucial tool for those who cannot speak. In Indonesia, Indonesian Sign Language (ISL) or Sistem Isyarat Bahasa Indonesia (SIBI) is officially recognized by the government and is taught in Special Schools (Sekolah Luar Biasa - SLB). The sign language dictionary comprises 3483 words, facilitating communication and participation in daily life for the deaf community. This research aims to convert ISL gestures within SIBI into understandable text, employing the Long-Short-Term Memory (LSTM) method as the primary approach. The study conducted experiments with two models: Model 1, using a smaller dataset, and Model 2, employing a larger dataset and implementing the k-fold method. The results indicate that Model 2 with k-fold accuracy achieved an accuracy of 98%, while Model 1 reached an accuracy of 85%. Nevertheless, challenges persist in these models, particularly in detecting words with similar gestures, such as’maaf’ (sorry) and 'cinta' (love), which may still be misidentified. Despite these challenges, this research contributes positively to the development of assistive technology for the deaf community, enabling more effective communication through sign language
Application design for web-based car services to increase work time estimates
No full textThe aim of this research is to increase the estimated service process time by creating an online-based car service ordering application at the Sinar Jaya repair shop and introducing information about Sinar Jaya car service services to the wider public. In this information systems research, the author of this research software development method uses the waterfall model development method. By implementing a waterfall, the research stages carried out by researchers start from data analysis, system analysis, system design, implementation, and testing. Creating a website-based car service ordering application at the Sinar Jaya Workshop can help customers find out the information available at the Sinar Jaya Workshop and the car service ordering process. Before there was an application, customers had to come to the location to place an order, so it took a long time to arrive at the location. So, with the online booking application, you can save time in the service process and get a queue number online. The data processing process for ordering car services becomes more practical so that it can be processed properly by the admin
Flood early warning system at Jakarta dam using internet of things (IoT)-based real-time fishbone method to support industrial revolution 4.0
Full text linkThis research aims to develop an effective flood early warning system to provide timely information to the public and support the government in disaster management. The Raspberry Pi mini-computer functions as the central control, collecting data from the Water Level Sensor to measure water height, the Ultrasonic Sensor for further monitoring, the DHT11 Sensor to monitor temperature and humidity, and a Buzzer as an audible warning device. The research method involves review of the literature and data acquisition from related journals. These data are utilized to design an Internet of Things (IoT)-based flood detection tool with the Raspberry Pi minicomputer as the main controller. The system can be implemented in vulnerable locations such as reservoirs, sluice gates, and rivers, as part of the Smart City and Smart Environment concepts. The test results indicate that the developed early warning system, integrating the Raspberry Pi minicomputer, the Water Level Sensor, the the Ultrasonic Sensor DHT11 Sensor, and Buzzer, approaches perfection. Real-time information is transmitted through the Twitter social media platform, which is shown to be more effective than manual notifications. The system can provide accurate early warnings, reduce flood-related damages, and positively contribute to flood prevention and disaster management efforts. This research is expected to make a significant contribution to improving the community and government preparedness for future flood disasters
Design and building system analysis on the smart fisheries village (SFV) website at the banyuwangi fisheries training and counseling center
Full text linkThis research aims to analyze and design a smart fisheries village-based website system to facilitate back-end, front-end, and UI/UX designers in the application of website creation according to the needs desired by the agency and with an organized database so that the creation of data reports will be faster. The early stages of the research began with the identification of the the specific needs of fishing villages and involved an in-depth analysis of the system needs that supported the vision of the Smart Fisheries Village. The design began with data collection consisting of observation methods and interviews, where researchers interviewed the authorities. In this method, the author gives 5 questions to the user, data analysis, and design of the Unified Modeling Language (UML). The design of this SFV web system uses a Unified Modeling Language (UML), which involves the use of diagrams and UML notation to describe various aspects of the system visually. The results of this study include UML diagrams, which encompass activity diagrams (for users and admins), flow diagrams (for users and admins), use case diagrams (for users and admins), and class diagrams that have undergone 4-5 iterations. The design of the Smart Fisheries Village website system is necessary to improve the welfare of the fishing village. Contributions of this research include the standardization of modeling, increased productivity, improved analysis and planning, and improved understanding. Previous research might have concentrated on a single type of system or domain. However, research should be expanded to various types of systems and industries
Application of k-nearest neighbor algorithm in classification of engine performance in car companies using Rapidminer
No full textImplementation of the k-Nearest Neighbor (k-NN) algorithm in the classification of CAR Car company engine performance using RapidMiner software. The company's engine performance is a very important aspect in the automotive industry that greatly affects operational efficiency and customer satisfaction. As an effort to monitor and improve engine performance, classification is an important key to identify machines that are feasible and require repair. The dataset used is a generated dataset from the AI Chat GPT bot whose prompts have been adapted to the research needs. The k-NN algorithm was chosen due to its ability to produce accurate predictions. The k-NN classification method utilizes training and testing data and calculates the distance between the data to determine the appropriate class. The results of this study show excellent performance in terms of accuracy, precision, and recall. The highest accuracy is 90.62% at the value of k = 2. The highest precision and recall are 100% and 93.75% at the values of k = 2, k = 4, and k = 7
Air quality monitoring using multi node slave IoT
Full text linkJakarta is the city with the second poorest air quality in the world. IQAir data show that Jakarta's air quality is 159. In addition, the concentration of air particles in Jakarta is 14.2 times higher than the annual guidelines of the World Health Organization (WHO). According to the WHO, exposure to air pollution causes around 7 million premature deaths and millions of years of lost health time each year. Air pollution also stunts children's growth, impairs lung function, etc. Therefore, we need a system that can be used to combine air quality to determine how dangerous a place is with air quality. Knowing air quality, certain policies or actions being taken to overcome this danger. This research aims to build and test a prototype air quality monitoring system using multi-node slaves with the Internet of Things. The prototype development process was carried out by adapting the architectural framework of the air quality monitoring system with the Internet of Things. The testing of prototype results is carried out to sound sensor values and functional success. The results of the test show that the system can run well according to the design made. The DSM501A sensor device functions to detect particles of a size larger than one micrometer, which usually include cigarette smoke, house dust, ticks, spores, pollen, and mildew, and works well so that the controller can read the surrounding air conditions well