Computer Science and Information Technologies (E-Journal)
Not a member yet
149 research outputs found
Sort by
Analysis of telehealth acceptance for basic life support training in sudden cardiac arrest in Pontianak
Full text linkSudden cardiac arrest (SCA), which is one of the most prevalent causes of mortality, can be prevented by quickly conducting basic life support (BLS). In Pontianak City, the challenges associated with obtaining emergency health training, such as BLS, remain high. This study aims to evaluate user acceptance of Telehealth as well as its effectiveness in BLS training. We will also discuss its impact on community knowledge and skills in managing cardiac arrest. We used the human, organization, and technology Fit (HOT-Fit) method to analyze the level of acceptance of Telehealth in BLS training. We collected data from 60 respondents who underwent Telehealth-based BLS training. The results showed that participants' understanding and readiness in dealing with heart attack emergencies had increased significantly, by 90% and 92%, respectively. Analysis of the level of acceptance with HOT-Fit showed that system quality had the greatest influence on system use (0.611). Service quality exerted the most significant impact on user satisfaction (0.568). The net benefit was influenced by system use, user satisfaction, and organizational support, with user satisfaction having the greatest influence (0.600). Further research will be conducted on the utilization of augmented reality (AR) or virtual reality (VR) technology to implement Telehealth for BLS training
Optimizing diplomatic indexing: full-parameter vs low-rank adaptation for multi-label classification of diplomatic cables
Full text linkAccurate classification of diplomatic cables is crucial for Mission’s evaluation and policy formulation. However, these documents often cover multiple topics, hence a multi-label classification approach is necessary. This research explores the application of pre-trained language models (CahyaBERT, IndoBERT, and MBERT) for multi-label classification of diplomatic cable executive summaries, which align with the diplomatic representation index. The study compares full-parameter fine-tuning and low-rank adaptation (LoRA) techniques using cables from 2022-2023. Results demonstrate that Indonesian-specific models, particularly the IndoBERT, outperform multilingual models in classification accuracy. While LoRA showed slightly lower performance than full fine-tuning, it significantly reduced GPU memory usage by 48% and training time by 69.7%. These findings highlight LoRA’s potential for resource-constrained diplomatic institutions, advancing natural language processing in diplomacy and offering pathways for efficient, real-time multi-label classification to enhance diplomatic mission evaluation
Cloud computing needs to explore into sky computing
Full text linkThis paper evaluates key issues in cloud computing and introduces a novel model, known as sky computing, to address these challenges. Cloud computing, a transformative technology, has played a critical role in reshaping modern operations—especially following the COVID-19 pandemic, when many human activities shifted to technology-driven platforms. It offers multiple service models, including Software as a Service, Hardware as a Service, Desktop as a Service, Backup as a Service, and Network as a Service, each tailored to user requirements. However, the rapid expansion of cloud-based technologies and interconnected systems has intensified infrastructure and scalability challenges. Sky computing, or the “cloud of clouds,” emerges as an advanced layer above traditional cloud models, enabling dynamically provisioned, distributed domains built over multiple serial clouds. Its core capability lies in offering variable computing capacity and storage resources with dynamic, real-time support, providing a robust and unified platform by integrating diverse cloud resources. This paper reviews related technologies, summarizes prior research on sky computing, and discusses its structural design. Furthermore, it examines the limitations of current cloud computing frameworks and highlights how sky computing could overcome these barriers, positioning it as a pivotal architecture for the future of distributed computing
An LSTM-based prediction model for gradient-descending optimization in virtual learning environments
Full text linkA virtual learning environment (VLE) is an online learning platform that allows many students, even millions, to study according to their interests without being limited by space and time. Online learning environments have many benefits, but they also have some drawbacks, such as high dropout rates, low engagement, and students' self-regulated behavior. Evaluating and analyzing the students' data generated from online learning platforms can help instructors to understand and monitor students learning progress. In this study, we suggest a predictive model for assessing student success in online learning. We investigate the effect of hyperparameters on the prediction of student learning outcomes in VLEs by the long short-term memory (LSTM) model. A hyperparameter is a parameter that has an impact on prediction results. Two optimization algorithms, adaptive moment estimation (Adam) and Nesterov-accelerated adaptive moment estimation (Nadam), were used to modify the LSTM model's hyperparameters. Based on the findings of research done on the optimization of the LSTM model using the Adam and Nadam algorithm. The average accuracy of the LSTM model using Nadam optimization is 89%, with a maximum accuracy of 93%. The LSTM model with Nadam optimisation performs better than the model with Adam optimisation when predicting students in online learning
Fingerprint based smart door lock system using Arduino and smartphone application
Full text linkIn 2023, crime cases in Indonesia will reach 105,133. Cases of theft with aggravation dominate the majority of cases. Everyone is concerned about safety, but doors are typically opened and closed using physical keys. This is vulnerable to being tampered with with fake keys, which can lead to house break-ins and theft. In this research, we propose a fingerprint-based wireless door lock design using Arduino and a smartphone. We offer this solution as a preventive measure to reduce the high rate of theft in homes or other buildings. The devices used are Arduino UNO R3, fingerprint sensor, HC-05 Bluetooth module, buzzer, and door lock solenoid. The results of the fingerprint-based wireless door lock using Arduino and a smartphone can function well, with an average response time of 1.20 seconds. Furthermore, testing the HC-05 Bluetooth when sending signals to a smartphone shows that it can read data accurately with an average response time of 1.54 seconds
Transfer learning: classifying balanced and imbalanced fungus images using inceptionV3
Full text linkIdentifying the genus of fungi is known to facilitate the discovery of new medicinal compounds. Currently, the isolation and identification process is predominantly conducted in the laboratory using molecular samples. However, mastering this process requires specific skills, making it a challenging task. Apart from that, the rapid and highly accurate identification of fungus microbes remains a persistent challenge. Here, we employ a deep learning technique to classify fungus images for both balanced and imbalanced datasets. This research used transfer learning to classify fungus from the genera Aspergillus, Cladosporium, and Fusarium using InceptionV3 model. Two experiments were run using the balanced dataset and the imbalanced dataset, respectively. Thorough experiments were conducted and model effectiveness was evaluated with standard metrics such as accuracy, precision, recall, and F1 score. Using the trendline of deviation knew the optimum result of the epoch in each experimental model. The evaluation results show that both experiments have good accuracy, precision, recall, and F1 score. A range of epochs in the accuracy and loss trendline curve can be found through the experiment with the balanced, even though the imbalanced dataset experiment could not. However, the validation results are still quite accurate even close to the balanced dataset accuracy
Trends in sentiment of Twitter users towards Indonesian tourism: analysis with the k-nearest neighbor method
Full text linkThis research analyzes the sentiment of Twitter users regarding tourism in Indonesia using the keyword "wonderful Indonesia" as the tourism promotion identity. This study aims to gain a deeper understanding of the public sentiment towards "wonderful Indonesia" through social media data analysis. The novelty obtained provides new insights into valuable information about Indonesian tourism for the government and relevant stakeholders in promoting Indonesian tourism and enhancing tourist experiences. The method used is tweet analysis and classification using the K-nearest neighbor (KNN) algorithm to determine the positive, neutral, or negative sentiment of the tweets. The classification results show that the majority of tweets (65.1% out of a total of 14,189 tweets) have a neutral sentiment, indicating that most tweets with the "wonderful Indonesia" tagline are related to advertising or promoting Indonesian tourism. However, the percentage of tweets with positive sentiment (33.8%) is higher than those with negative sentiment (1.1%). This study also achieved training results with an accuracy rate of 98.5%, precision of 97.6%, recall of 98.5%, and F1-score of 98.1%. However, reassessment is needed in the future as Twitter users' sentiments can change along with the development of Indonesian tourism itself
Implementing lee's model to apply fuzzy time series in forecasting bitcoin price
Full text linkOver time, cryptocurrencies like Bitcoin have attracted investor's and speculators' interest. Bitcoin's dramatic rise in value in recent years has caught the attention of many who see it as a promising investment asset. After all, Bitcoin investment is inseparable from Bitcoin price volatility that investors must mitigate. This research aims to use Lee's Fuzzy Time Series approach to forecast the price of Bitcoin. A time series analysis method called Lee's Fuzzy Time Series to get around ambiguity and uncertainty in time series data. Ching-Cheng Lee first introduced this approach in his research on time series prediction. This method is a development of several previous fuzzy time series (FTS) models, namely Song and Chissom and Cheng and Chen. According to most previous studies, Lee's model was stated to be able to convey more precise forecasting results than the classic model from the FTS. This study used first and second orders, where researchers obtained error values from the first order of 5.419% and the second order of 4.042%, which means that the forecasting results are excellent. But of both orders, only the first order can be used to predict the next period's Bitcoin price. In the second order, the resulting relations in the next period do not have groups in their fuzzy logical relationship group (FLRG), so they can not predict the price in the next period. This study contributes to considering investors and the general public as a factor in keeping, selling, or purchasing cryptocurrencies
Smart irrigation system using node microcontroller unit ESP8266 and Ubidots cloud platform
Full text linkThe agricultural irrigation system is extremely important. For optimal harvest yields, farmers must manage rice plant quality by monitoring water, soil, and temperature on agricultural fields. If market demand rises, traditional rice field irrigation in Indonesia will make things harder for farmers. This modern era requires a system that lets farmers monitor and regulate agricultural fields anywhere, anytime. We need a solution that can control the irrigation system remotely using an internet of things (IoT) device and a smartphone. This study employed the Ubidots IoT cloud platform. In addition, the study uses soil moisture and temperature sensors to monitor conditions in agricultural regions, while pumps function as irrigation systems. The test results indicate the proper design of the system. Each trial collected data. The pump will turn on and off automatically based on soil moisture criteria, with the pump active while the soil moisture is less than 20% and deactivated when the soil moisture exceeds 20%. In simulation mode, the pump operates for an average of 0–5 seconds of watering. The monitoring system shows the current soil temperature and moisture levels. Temperature sensors respond in 1-3 seconds, whereas soil moisture sensors respond in 0–4 seconds
Clustering man in the middle attack on chain and graph-based blockchain in internet of things network using k-means
Full text linkNetwork security on internet of things (IoT) devices in the IoT development process may open rooms for hackers and other problems if not properly protected, particularly in the addition of internet connectivity to computing device systems that are interrelated in transferring data automatically over the network. This study implements network detection on IoT network security resembles security systems from man in the middle (MITM) attacks on blockchains. Security systems that exist on blockchains are decentralized and have peer to peer characteristics which are categorized into several parts based on the type of architecture that suits their use cases such as blockchain chain based and graph based. This study uses the principal component analysis (PCA) to extract features from the transaction data processing on the blockchain process and produces 9 features before the k-means algorithm with the elbow technique was used for classifying the types of MITM attacks on IoT networks and comparing the types of blockchain chain-based and graph-based architectures in the form of visualizations as well. Experimental results show 97.16% of normal data and 2.84% of MITM attack data were observed