Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI

Forest Fire Detection Using Transfer Learning Model with Contrast Enhancement and Data Augmentation

Vina Ayumi, Handrie Noprisson, Nur Ani — Sun, 31 Mar 2024 00:00:00 +0000

Forest damage due to fire is unique of the catastrophes that can disrupt and damage the existing ecosystem. There needs to be a quick response to fires because disaster management takes longer, and the impact of the damage will be more severe. To process images to detect fire in the forest, we need to build a suitable deep-learning model. This study proposed research on forest fire detection using an Xception and MobileNet model. Moreover, this research optimizes the accuracy of the model by applying Contrast-Limited-Adaptive-Histogram-Equalization (CLAHE) and data augmentation to tackle the problem of the forest fire image dataset. Based on the experiment, MobileNet with CLAHE obtained 99,66% accuracy in the test phase. In the same phase, MobileNet with CLAHE obtained a value F1-score of 1.00, a value of precision of 0.99, and a value of recall of 1.00. If compared to other model performances, MobileNet with CLAHE obtained the best result.

Parallel Hybrid Particle Swarm-Grey Wolf Algorithms for Optimal Load-Shedding in An Isolated Network

Sujono, Ardyono Priyadi, Margo Pujiantara, Mauridhi Hery Purnomo — Sun, 31 Mar 2024 00:00:00 +0000

In distribution networks integrated with distributed generation (DG), disconnection from the main grid reduces the power supply significantly. The power imbalance between DG generation and load degrades network stability. This paper proposes a hybrid parallel Particle Swarm Optimization - Grey Wolf Optimizer (PSGWO) algorithm for load shedding optimization. This optimization aims to reduce the DG power not absorbed by the remaining loads and maintain the voltage within the specified limits. The performance of PSGWO is tested on an IEEE 33 bus radial distribution system, considering loading levels of 80% to 140% of the baseload. At a 100% loading level, PSGWO showed the best performance, with a load shedding of 2.2297 MW and a voltage deviation of 0.0049. These values are the smallest compared to the results of the standard PSO and GWO algorithms. The PSGWO algorithm remains superior and converges faster than standard PSO and GWO at all loading levels.

SARIMA with Sliding Window Implementation for Forecasting Seasonal Demand Data

Made Rama Pradipta, Gusti Made Arya Sasmita, Anak Agung Ngurah Hary Susila — Sun, 31 Mar 2024 00:00:00 +0000

Demand forecasting is an essential part of business process management. A comparison of methods is needed to get the best model to provide good forecasting results. Difficulties in meeting consumer demands and predicting these requests using demand data at companies CV. ABCD is the main problem in this research. The SARIMA and decomposition methods are used for comparison and search for the best model before forecasting. SARIMA with a windowing size of 56, indicating the smallest MAPE value of 3,91%. The value <10%, so it can be said to produce an excellent forecasting value. Forecasting results with SARIMA show a meeting between actual and forecasting data in 2022. Therefore, it can be said the forecasting results for 2023 and 2024 can be used as a reference for the company CV. ABCD to meet customer demand and avoid stock shortages.

Analysis Quality of Employment Information Systems Using Webqual 4.0 and Importance Performance Analysis Method

Bagus Premana Putra I Gede, Sudarma Made, Gunantara Nyoman — Sun, 31 Mar 2024 00:00:00 +0000

Information system quality analysis is an aspect that information system managers must pay attention to, especially to meet user needs, increase comfort, and increase user productivity. SISNAKER, as the main information system used by the Department of Manpower and Energy and Mineral Resources of Bali Province to support services to the community digitally, also requires a quality analysis process to ensure user comfort when interacting with SISNAKER. This research aims to measure the quality of the employment information system, often called SISNAKER belonging Department of Manpower and Energy and Mineral Resources of Bali Province based on user perceptions and provide recommendations to improve the system quality. SISNAKER quality is measured using a questionnaire based on domains of the WebQual 4.0 method especially, usability, information quality, and interaction quality parameters. Mapping recommendations to improve SISNAKER quality is made based on four priority quadrants of the Importance Performance Analysis (IPA) method. The sampling of research was based on a proportionate stratified random sampling technique, involving a total of 98 respondents. The results of the research show that the gap between performance and user expectations is 0.02, which means that system performance is in line with user expectations. Improvement is found in information quality and interaction quality parameters, with -0.02 gap, so it still needs improvement.

Adaptive Threshold Filtering to Reduce Noise in Elderly Activity Classification Using Bi-LSTM

Sun, 31 Mar 2024 00:00:00 +0000

As the global population ages, there is an increasing need to provide better care and support for older individuals. Deep learning support to accurately predict elderly activities is very important to develop. This research discusses a new model integrating filtering techniques using adaptive thresholds with Bidirectional - Long Short-Term Memory (Bi-LSTM) networks. The problem of activity prediction accuracy, mainly due to noise or irrational measurements in the dataset, is solved with adaptive thresholds. Adaptive characteristics at the threshold are needed because each individual has different activity patterns. Experiments using the HAR70+ dataset describe the activity patterns of 15 elderly subjects and the gesture patterns of 7 activities. Based on body movement patterns, the elderly can be classified as using walking aids. The proposed model design obtains an accuracy of 94.71% with a loss of 0.1984.

Random Forest-Based Assessment of Mangrove Degradation Utilizing NDVI Feature Extraction in Spatio-Temporal Analysis

Hadi Santoso, Syahrul Hidayatullah — Sun, 31 Mar 2024 00:00:00 +0000

Mangrove ecosystems, vital for coastal biodiversity and protection, confront escalating degradation from human and natural influences. Addressing the imperative for precise degradation assessment, this study introduces a Random Forest-based technique, utilizing NDVI (Normalized Difference Vegetation Index) feature extraction within a spatio-temporal framework. The principal aim is to establish a robust approach for evaluating mangrove degradation and land cover shifts. This involves extracting NDVI values from satellite images to monitor vegetation health and changes chronologically. Leveraging the Random Forest algorithm, acknowledged for managing intricate relationships and classifications, further enhances the methodology.By situating the approach spatio-temporally, degradation patterns and alterations in mangrove distribution are traced over time. The temporal progression of the study area is considered, affording a thorough degradation analysis. Outcomes affirm the method's efficacy, evidenced by a Cohen's Kappa Score of 0.96 denoting substantial agreement between predictions and observations. Remarkably high scores across accuracy, precision, recall, and F1-score (all at 0.97) underscore the model's precision in classifying mangrove degradation levels. The amalgamation of the Random Forest-based approach and NDVI feature extraction emerges as a valuable instrument for precise mangrove degradation assessment. The spatio-temporal analysis augments comprehension of degradation dynamics, pivotal for proficient mangrove management and conservation strategies.

Bank Customer Segmentation Model Using Machine Learning

Sun, 31 Mar 2024 00:00:00 +0000

Banks generally carry out marketing strategies by offering deposit products directly to customers. However, this method is less effective because it requires individualized communication without considering the customer's interest in the product offered. Therefore, this research aims to categorize the classification of bank customers into Yes and No. This research uses a dataset of bank deposits taken from KTM. This research uses a bank deposit dataset taken from Kaggle, the data consists of 11162 rows with 17 attributes. PCA technique was used for feature selection which was optimized by reducing the dimensionality of the dataset before modeling. It was found that the best model accuracy was SVM RBF kernel with C parameters achieving 80.51% accuracy and ANN 80.78%, but ANN showed a higher ROC graph than SVM because ANN performance results were faster than SVM. Thus, the overall performance measurement of ANN is much better.

Image Classification of Balinese Seasoning Base Genep Based on Deep Learning

I Putu Widia Prasetia, I Made Gede Sunarya — Sun, 31 Mar 2024 00:00:00 +0000

One of Indonesia's abundant natural wealth is spices and seasonings. Base Genep is a basic spice in making traditional Balinese culinary preparations. Base Genep uses many spices and seasonings, including turmeric, ginger, galangal, galangal, candlenuts, nutmeg, pepper, shallots, garlic, coriander, lemongrass, and cloves. From the variety of spices and seasonings that exist in Indonesia, it turns out that the knowledge of the Indonesian people is still low regarding spices and seasonings, especially among the younger generation. This is because these spices/seasonings have characteristics, shapes, and skin colors that are almost similar at first glance, making them difficult to differentiate. Based on these problems, this research was carried out with the aim of helping the public, especially the younger generation, recognize and differentiate types of spices and seasonings. Therefore, in this research, a model based on Deep Learning technology was created. The general objective of this research is to classify spices/seasonings which are often used as basic ingredients in the manufacture of Bumbu Bali Base Genep such as ginger, aromatic ginger, turmeric, and galangal using the YOLOv8 model. The data used in this study were obtained with a smartphone. The data consists of 1200 images consisting of 4 classes. The data is divided into several parts, namely training data, validation and testing data. The resulting dataset is divided into 4 dataset schemes in conducting model training. The highest score for the model in this study was obtained in dataset scheme number 4.

Enhancing Rice Production Prediction: A Comparative Machine Learning Analysis of Climate Variables

Roni Yunis, Sudarto, Irpan Adiputra Pardosi — Sun, 31 Mar 2024 00:00:00 +0000

This study aims to enhance rice production prediction through a comparative analysis of machine learning models utilizing climate variables. Eight models were assessed on a predetermined dataset, with Support Vector Regression (SVR) emerging as the top performer. Following the identification of significant climate variables influencing rice production, the models underwent evaluation using two hyperparameter approaches: random search and manual tuning. SVR outperformed other models, achieving impressive metrics with MAE 0.180, MSE 0.186, RMSE 0.431, and an exceptionally low MAPE of 0.020. Key factors influencing rice production included productivity and area, along with humidity, rainfall, temperature, wind velocity, and sunshine duration. Favorable conditions for rice output encompassed low humidity, moderate rainfall, increased wind speed, and prolonged sunshine, while rainfall and temperature exhibited minimal impact. The success of random search emphasizes the importance of effective hyperparameter tuning. This research provides valuable insights for enhancing rice production prediction.

Development of Virtual Reality for Optical Fiber Splicing Simulation

Rahmat Gah Bahaduri, I Gede Partha Sindu, Dessy Seri Wahyuni — Sun, 31 Mar 2024 00:00:00 +0000

This study aims to determine the design and evaluation of content and media experts in the development of Virtual Reality for Optical Fiber Splicing Simulation. The research method used is Research & Development with the Multimedia Development Life Cycle (MDLC) model which consists of concept, design, material collecting, assembly, testing, and distribution stages. This Virtual Reality development uses the Unity application in making applications with the Oculus Quest 2 device. The data collection process begins with interviews with educators about the learning that takes place, and the difficulties experienced. At the testing stage, Blackbox Test, Content Expert Test: 1.00 Validity Coefficient, and Media Expert Test: 1.00 Validity Coefficient. Virtual Reality for Fiber Optic Splicing Simulation offers simulation before implementing splicing in real. By taking characteristics of life such as laboratories, educators, and fiber optic practicum tools. Virtual reality can provide situations and conditions for students to practice Optical Fiber Splicing by entering a virtual laboratory in cyberspace. The learning experience in Virtual Reality that provides a sense of immersion in a virtual environment using Full Hand Interaction that applies the Hand Tracking function in Oculus Quest 2. Based on the overall test, the development of Virtual Reality for Optical Fiber Splicing Simulation is feasible to use and distribute to target students.

Development of Augmented Reality Application as An Educational Media for Visitors to Museum Pusaka Keraton Kasepuhan Cirebon Using Object Tracking Method and Fast Corner Detection Algorithm Based on Android

Yuhano, Faisal Akbar — Sun, 31 Mar 2024 00:00:00 +0000

Augmented Reality is a technology that combines two-dimensional or three-dimensional virtual objects and projects these virtual objects in real time. One implementation of Augmented Reality in the tourism sector is to educate museum visitors. Museum Pusaka Keraton Kasepuhan Cirebon does not yet have a touch of technology to attract visitors, and the public paradigm is that visiting the museum only sees heirloom objects, nothing interesting or unique. The aim of the research carried out by the author is to apply Augmented Reality with the Object Tracking method and the FAST Corner Detection algorithm to educate museum visitors, so that it can attract visitors' attention. By utilizing these methods and algorithms, it can be easier for visitors to explore heirloom objects to obtain the desired information. So the results obtained from the research conducted by the author are that the response time for objects appearing using the Tracking Object method and the FAST Corner Detection algorithm in environments that use glass is an average of 1.52 seconds to 2.40 seconds and that does not use glass, namely 2.84 seconds to 4.71 seconds with a level of confidence at the 95% level.

The Significance of Dynamic COVID-19 Dashboard in Formulating School Reopening Strategies

Sun, 31 Mar 2024 00:00:00 +0000

Experiments conducted with the COVID-19 dataset have predominantly concentrated on predicting cases fluctuating and classifying lung-related diseases. Nevertheless, the consequences of the COVID-19 pandemic have also spread to the education sector. To safeguard educational stability in response to the remote learning policy, we leverage authentic COVID-19 datasets alongside school information across 154 sub-areas in Surabaya City, Indonesia. Our focus is predicting the dynamic within these sub-areas where schools are located. The outcomes of this study, by incorporating the recurrent neural network of long- and short-term memory (RNN-LSTM) architecture and refined hyperparameters, effectively enhanced the predictive model's performance. The findings are showcased on a dashboard, visually representing the transmission of COVID-19 in schools across each sub-area. This information serves as a basis for informed decisions on the safe reopening of schools, aiming to mitigate the decline in education quality during the challenging pandemic.

Particle Swarm Optimization for Optimizing Public Service Satisfaction Level Classification

Tyastuti Sri Lestari, Ismaniah Ismaniah, Wowon Priatna — Sun, 31 Mar 2024 00:00:00 +0000

This research aims to categorize survey data to determine the level of satisfaction with the services provided by the village government as a public service provider. Villages or sub-districts currently offer services in response to community demand, although only partially or as efficiently as possible. The data collection technique used was distributing questionnaires to the village community. The method used for classification is the machine learning method. Before the classification process, feature selection is carried out at the data pre-processing stage using Particle Swarm Optimization (PSO), which has been proven to increase the accuracy of the classification values. The classification methods employed include Decision Tree (DT), Naive Bayes, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms for classification purposes. This study achieves the maximum level of accuracy in decision tree classification, attaining an accuracy rate of 97.74%. Subsequently, the KNN algorithm achieved an accuracy of 77.90%, the Nave Bayes algorithm achieved 64.4%, and the SVM algorithm, which yielded the lowest accuracy value, achieved 59.90%. Following the application of Particle Swarm Optimization (PSO) for optimization, the accuracy of the SVM and KNN algorithms improved to 98.3%. The Decision Tree algorithm achieved a value of 97.77%, while the Naive Bayes technique yielded a value of 69.30%.

Incorporating Stock Prices and Social Media Sentiment for Stock Market Prediction: A Case of Indonesian Banking Company

Sun, 31 Mar 2024 00:00:00 +0000

Forecasting the stock market is one of the most popular topics to be discussed in many fields. Many studies, especially in information technology have been conducted machine learning algorithms to achieve a more accurate prediction of the stock market. This research aims to find the effectiveness in predicting stock market performance by utilizing social media sentiment in combination with historical data. In addition, this research uses a machine learning algorithm to train a model to predict the stock price of each bank and training the model on a dataset that included the historical stock prices of the bank, as well as the sentiment scores of the social media posts about the bank and evaluate the performance of the model by comparing the predicted stock prices to the actual stock prices. The research shows that the R2 and RMSE score model that has been built with its historical data has slightly better performance than the model that has been built with the combination of historical data and social media sentiment. The finding indicates that the research method is closely correlated and affected to the performance of the stock market prediction.

Comparison of K-NN, SVM, and Random Forest Algorithm for Detecting Hoax on Indonesian Election 2024

Sun, 31 Mar 2024 00:00:00 +0000

During the year 2022, The Indonesian National Police (POLRI) received 113 reports related to the spread of hoax news related to 2024 Indonesian Election (PEMILU). There are still relatively few hoax detection tools that already exist in Indonesia. This research creates a system that can detect hoax news in Indonesian tweets about the Indonesian Election (PEMILU) 2024 by comparing three methods, namely K-NN, SVM, and Random Forest. The process of labeling (create model) using validation on ground truth data, namely cekfakta.tempo, cekfakta.kompas, and turnbackhoax.id. In this research, we also check the differences between different types of distance measurements in applying the K-NN algorithm. The method used for feature extraction in this research is TF-IDF. The results of experiments show that the highest accuracy results are obtained using the SVM and K-NN algorithms with distance measurements using Euclidean Distance, which is 86.36%. The best precision value is obtained using the K-NN algorithm with distance measurements using Manhattan Distance, which is 86.95%.

Mobile Applications for Self-Handle of Pornography Addiction

Raditya Muhammad, Mochamad Iqbal Ardimansyah, Yona Wahyuningsih — Sun, 31 Mar 2024 00:00:00 +0000

Content with pornographic nuances in the form of images, sound, and videos is widely circulating on the internet, including on social media. Teenagers have great potential to become addicted to pornographic content given the widespread use of the internet among adolescents. Pornography addiction has the potential to interfere with the physical and mental development of addicts, even a wider impact can lead to criminal cases in society, such as rape. This paper discusses the development of mobile applications that aim to help pornographic content addicts get rid of pornography addiction problems. The applications developed include a system for assessing the level of exposure to pornographic content, handling and self-care of pornographic content, and a system for detecting the user's location in solitude. The rating system was adapted from the Pornography Addiction Screening Tool (PAST). Handling and self-care pornographic content use the psychological approach of Cognitive Behavioral Therapy (CBT) which has been widely researched and used as a method for mental treatment and healing. An assessment system for the level of exposure to pornographic content and self-care is presented in the application by utilizing chatbot to increase the interactive between the user and the application. The research method uses the Design Research Methodology (DRM) while the method in developing mobile applications uses Agile models as an adaptive software development method. This application is not intended to replace the role of psychologists, but as a supporting tool that can help pornography addicts to reduce their addiction level until they recover. Through black box testing, evaluation results from a functional perspective show that this application can be used as expected.