JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
CNN-LSTM for Heartbeat Sound Classification
Get PDFCardiovascular disorders are among the primary causes of death. Regularly monitoring the heart is of paramount importance in preventing fatalities arising from heart diseases. Heart disease monitoring encompasses various approaches, including the analysis of heartbeat sounds. The auditory patterns of a heartbeat can serve as indicators of heart health. This study aims to build a new model for categorizing heartbeat sounds based on associated ailments. The Phonocardiogram (PCG) method digitizes and records heartbeat sounds. By converting heartbeat sounds into digital data, researchers are empowered to develop a deep learning model capable of discerning heart defects based on distinct cardiac rhythms. This study proposes the utilization of Mel-frequency cepstral coefficients for feature extraction, leveraging their application in voice data analysis. These extracted features are subsequently employed in a multi-step classification process. The classification process merges a convolutional neural network (CNN) with a long short-term memory network (LSTM), forming a comprehensive deep learning architecture. This architecture is further enhanced through optimization utilizing the Adagrad optimizer. To examine the effectiveness of the proposed method, its classification performance is evaluated using the "Heartbeat Sounds" dataset sourced from Kaggle. Experimental results underscore the effectiveness of the proposed method by comparing it with simple CNN, CNN with vanilla LSTM, and traditional machine learning methods (MLP, SVM, Random Forest, and k-NN)
Text Mining for News Forecasting on The Turnback Hoax Website
Get PDFNews has been disseminated swiftly via the internet due to the rapid growth of information technology. The rapid spreading of news often confuses because the truth cannot be ascertained. Additionally, online social media is becoming increasingly popular, making it an excellent environment for propagating false information, including misinformation, phony reviews, advertising, rumors, political remarks, innuendo, etc. This study's specific goal is to classify data using a data mining approach model called text mining so that a system can automatically do the classification. As a result, the study will produce a dataset, which can then be used to create an application using data mining's ability to predict breaking news. An application was produced by employing data mining to forecast recent news. This study was able to classify data using a naive Bayes data mining approach model so that a system can automatically do the classification. The study produced an accuracy of 77% obtained with training data of 82%. From 994 contents, the classification of misleading content reached 33.9%, false content as many as 24.85%, imitation content was 13.48%, fake content reached 11.07%, manipulated content was 9.86%, parody content was 3.22%, satire content was 2.31%, and connection content as many as 1.31%. This study then visualizes the results using bar charts and word clouds. This work also produced datasets with the naïve Bayes method of news data and news that has been valid. Afterward, the dataset will be used in making applications to produce prototypes of computer program applications
An Experimental Study on Deep Learning Technique Implemented on Low Specification OpenMV Cam H7 Device
Get PDFThis research aims to identify and recognize the OpenMV Camera H7. In this research, all tests were carried out using Deep Machine Learning and applied to several functions, including Face Recognition, Facial Expression Recognition, Detection and Calculation of the Number of Objects, and Object Depth Estimation. Face Expression Recognition was used in the Convolutional Neural Network to recognize five facial expressions: angry, happy, neutral, sad, and surprised. This allowed the use of a primary dataset with a 48MP resolution camera. Some scenarios are prepared to meet environment variability in the implementation, such as indoor and outdoor environments, with different lighting and distance. Most pre-trained models in each identification or recognition used mobileNetV2 since this model allows low computation cost and matches with low hardware specifications. The object detection and counting module compared two methods: the conventional Haar Cascade and the Deep Learning MobileNetV2 model. The training and validation process is not recommended to be carried out on OpenMV devices but on computers with high specifications. This research was trained and validated using selected primary and secondary data, with 1500 image data. The computing time required is around 5 minutes for ten epochs. On average, recognition results on OpenMV devices take around 0.3 - 2 seconds for each frame. The accuracy of the recognition results varies depending on the pre-trained model and the dataset used, but overall, the accuracy levels achieved tend to be very high, exceeding 96.6%
Econometric Model Using Arbitrage Pricing Theory and Quantile Regression to Estimate the Risk Factors Driving Crude Oil Returns
Get PDFThis work presents a novel approach to determining the risk and return of crude oil stocks by employing Arbitrage Pricing Theory and Quantile Regression. Arbitrage Pricing Theory identifies the risk factors likely to impact crude oil returns. Subsequently, Quantile Regression estimates the relationship between the selected factors and the returns across different distribution quantiles. The West Texas Intermediate (WTI) crude oil price is used in this study as a benchmark for crude oil prices. WTI’s price fluctuations can significantly impact the performance of global crude oil stocks and, subsequently, the global economy. Various statistical measures are used in this study to determine the proposed model's stability. The results show that changes in WTI returns can have varying effects depending on market conditions and levels of volatility. This study emphasizes the influence of structural discontinuities on returns. These are likely generated by changes in the global economy and the unpredictable demand for crude oil during the pandemic. The inclusion of pandemic, geopolitical, and inflation-related explanatory variables adds uniqueness to the study as it considers current global events that can affect crude oil returns. Findings show that the key factors that pose significant risks to returns are industrial production, inflation, the global price of energy, the shape of the yield curve, and global economic policy uncertainty. This implies that while making investment decisions in WTI futures, investors should pay particular attention to these elements
Text-Based Content Analysis on Social Media Using Topic Modelling to Support Digital Marketing
Get PDFThis study aims to create Social Media Analytics (SMA) tools to help Digital Marketers or Content Creators create content topics for creating text-based Instagram content and support digital marketing strategy. Since no SMA tools can provide topic discovery for text-based Instagram content, this research aims to make an SMA tool. The data requirements to make an SMA tool include content text, content caption text, likes, comments, upload time, and content category obtained through the Instascrapper. The method used in this study is the Topic Modelling method using the Latent Dirichlet Allocation (LDA) approach to find the most dominant topic in the content. Optical Character Recognition (OCR) performs an image transformation process to extract text from text-based Instagram content images. The results of SMA tool creation are tested on three expert users, which shows that 93% of test participants could use the SMA to find topic references, and 85% can still be used by users even though they find it difficult. Since the test result shows that SMA tools still need development, for further research, SMA tools can focus on developing the user experience to increase the value of user acceptance by paying attention to the ease of the SMA tools. Also, SMA tools can focus on target users such as Data Analysts, Business Intelligence Analysts, or others within a company to support decision-making for the marketing department
Automated Matching Skills to Improve the Accuracy of Job Applicant Selection Using Indonesian National Work Competency Standards
Get PDFThe high number of cyberattack anomalies and data leaks in Indonesia increases the need for cybersecurity in various companies. Cybersecurity capabilities and skills in Indonesia are divided into three categories based on the Indonesian National Work Competency Standards (SKKNI), namely Security Operation Center (SOC), Cybersecurity test/Penetration testing (Pentest), and Information Security Audit. Although various approaches have been applied in different companies to select job applicants, a new method with automated matching is explored in this study. This method matches the skills possessed by prospective job applicants with the profile of their job task requirements based on the SKKNI Decree of the Minister of Manpower of the Republic of Indonesia using Machine Learning (ML) models. The empirical comparison of results comes from automated matchmaking processed by Multinomial Naive Bayes (MNB) and Decision Tree algorithm models. Before modeling, the data is trained and evaluated for testing. Then to assess the most optimal algorithm between MNB and Decision Tree, a confusion matrix is proposed and used to find the best model. From the evaluation results, both models performed well and were highly accurate during training and test evaluation. The Decision Tree model performs slightly better than the MNB model, but both still provide satisfactory results in classifying data based on the Indonesian National Work Competency Standards (SKKNI) categories. This study offers a solution to minimize the number of potential applicants who are not competent in the three SKKNI cybersecurity job categories due to the mismatch of their abilities and skills
CSS for CVR: A Reciprocal Velocity Obstacle-Based Crowd Simulation System for Non-Playable Character Movement of Campus Virtual Reality
Get PDFAlong with the development of multimedia technology, an overview of the campus environment for prospective new visitors can be visualized through a 3D virtual environment based on virtual reality. A crowd simulation system is needed to provide an overview of the crowds in campus virtual reality (CVR). The simulation helps make it easier for individuals to predict crowds in certain areas virtually. In this study, we propose using the Reciprocal Velocity Obstacle (RVO) method to support the simulation of Non-Playable Character (NPC) crowds in a visualized virtual environment. RVO implements multi-agent navigation by estimating the possibility of moving without communication between agents and being able to perform collision avoidance. The use of RVO in this study aims to contribute to the collision detection development process for each NPC. The application of RVO is carried out in the development of virtual reality by using Unity3D and Blender asset support tools. The results of this study indicate that the RVO method can be applied in multi-agent navigation. These results were confirmed by the success of the NPC as a simulation agent in selecting routes and independently navigating to avoid collisions between agents without the need for communication. In every simulation, collisions will occur within a set of agents due to high density, which causes complex computations. The development of CSS can help every CVR user experience a virtual environment. In addition, each user can experience a more natural experience with the presence of 3D objects and virtual reality with RVO-based CSS. Furthermore, this research material is expected to be developed from various perspectives and themes related to crowd simulation for games and other simulation media
Indonesian Fake News Classification Using Transfer Learning in CNN and LSTM
Get PDFFake news spreads quickly and is challenging to stop due to the ease of accessing and sharing information online. Deep learning techniques are a method that can be used to identify fake news quickly and accurately. The types of neural networks commonly utilized in deep learning architectures include Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), which can perform well when managing the task of classifying fake news, according to several pertinent studies. Regarding handling instances of Indonesian fake news classification, this study compares how well the CNN and LSTM models perform. However, given that Indonesian is a low-resource language with scant documentation, it is challenging to build an adequate data set. At the same time, the CNN and LSTM classification models require significant training data. We proposed a transfer learning method by combining two classification models with a pre-trained IndoBERT language model. 1340 news text data were used, including 643 actual news texts from CNN Indonesia, Liputan6, and Detik and 697 fake news texts from TurnBackHoax. As a result, the performance of the combination of the LSTM classification model with IndoBERT outperformed that of the CNN classification model with IndoBERT, which only produced an accuracy of 92.91%, down by 6%, and was able to produce an accuracy of up to 97.76%, an increase of 4.8% from before. Furthermore, the results show that the LSTM classification model outperforms the CNN classification model in capturing the representation created by IndoBERT. Additionally, these insights may serve as a basis for future research on identifying fake news in Indonesia, helping to improve methods for combatting misinformation in Indonesia
Big Mart Sales Data Visualization and Correlation
Get PDFThe amount of unprocessed data available every day is growing. This massive amount of data needs to be effectively assessed to give results that are extremely useful. In the present day, it is crucial for inventory management and demand forecasting to collect sales data for commodities or things, together with all their numerous dependent or independent parts. In a Big Mart Company, the use of sales forecasting is to estimate numerous goods that are readily available and supplied at multiple retailers in different towns. As the number of products and outlets increased drastically, it became increasingly difficult to forecast them manually. As a result, it is necessary to see to what extent the relationship between several variables, including price, popularity, time of day, outlet type, outlet location, etc., affects the appeal of a product. In this research, a data cleaning process was carried out, and data visualization using scatter plots, as well as finding Pearson correlations. The raw processing the data with study of a case big mart sales data is taken from the Kaggle website [https://www.kaggle.com/datasets/sandeepgauti/bigmart-sales]. The Pearson correlation test determines a lack of connection between the two Item_Weight and Item_Outlet_Sales variables. There is a strong but negative correlation where if Item_Visibility decreases, Item_Outlet_Sales also decreases. Positive relationships exist between the two Item_MRP and Item_Outlet_Sales variables. In addition to the correlation test, descriptive statistical analysis is also performed here. With this simple data processing, the raw data will be better organized and easier to analyze, read, and use
Predictive Wireless Received Signal Strength Using Friis Transmission Technique
Get PDFA good WLAN performance is crucial in determining the quality of experience (QoE) among the campus community. Proper WLAN planning and design should be done beforehand to ensure good WLAN performance. Various studies have discussed different methods of conducting WLAN planning to predict WLAN's best performance, including using artificial intelligence and mathematical approaches. One of the processes involved in performing WLAN planning is measuring performance parameters. Signal strength is one of the vital parameters to be measured in determining the excellent performance of WLAN in a particular area. When deploying a WLAN design in two different environments, the signal strength outcomes can differ due to various factors, including obstacles and path loss propagation issues within the deployment area. Higher Learning Institutions (HLIs) present a unique challenge as their building designs vary to accommodate student needs. As a result, the selection of materials used will also be different, affecting the WLAN performance. A detailed study should investigate the effect of path loss propagation and the type of obstacle that affects WLAN performance in HLI. Thus, this study focuses on predicting received signal strength using Friis Transmission and studying the effect of path loss propagation on WLAN performance. The simulated model significantly affects signal strength when the signal passes through different types of building material (non-LOS) and line-of-sight (NLOS), where concrete walls substantially affect the received signal strength between transmitters. The proposed model can assist network planners in designing robust WLAN infrastructure by improving signal strength, particularly in the HLI WLAN environment.Â