Journal of Computer Networks, Architecture and High Performance Computing
Not a member yet
473 research outputs found
Sort by
BITCOIN PRICE PREDICTION USING LONG SHORT TERM MEMORY ALGORITHM
Full text linkBitcoin a digital asset with the largest market capitalization in the world and shows high price volatility, attracting the interest of researchers to make accurate price predictions. The research aims to build a Bitcoin price prediction model use Long Short-Term Memory (LSTM) algorithm by utilizing closing price data and technical indicator variables, Moving Average (MA) and Exponential Moving Average (EMA). Dataset obtained from Yahoo Finance with a time range of January 1, 2015 to January 1, 2024 as much as 3287 data. The LSTM model is designed in multivariate form with an input sequence of 30 with several test scenarios at the epoch number 50, 100 and 200. Model evaluation is based on 4 metrics, namely Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Abso-lute Percentage Error (MAPE). Model evaluation results show that the model is capable of providing a good prediction value with an MSE value of 0.0001, RMSE of 0.0117, MAE of 0.0081, and MAPE of 2.21% at epoch 200. The use of technical indicators proved to be helpful in improving the performance of the model compared to using only closing price data
Real-Time Data Integration and Weather Reporting Automation with Cloud Computing-based Interactive Spatial Dashboard for Extreme Weather Risk Analytics in Indonesia
Full text linkGlobal climate change has increased the risk of extreme weather events in Indonesia, necessitating an accurate and real-time weather information system. This study develops a cloud computing-based system capable of integrating national weather data in real-time, automating the generation of actual and forecast weather reports, and presenting this information through an interactive spatial dashboard. The system is built on a client-server architecture deployed on Google Cloud Platform, utilizing the OpenWeatherMap API, a Flask backend, and a JavaScript-based frontend (Leaflet.js and Chart.js). Evaluation results indicate that the system can provide integrated national weather data with latency under one second, generate automated multi-province weather reports, and deliver interactive heatmap visualizations of extreme weather risks. This system is effective in improving the speed, accuracy, and efficiency of weather information distribution to support decision-making in the maritime, transportation, and disaster management sectors
Strategic Planning of Information Systems and Technology Using the Ward and Peppard Method at Politeknik Internasional Bali
Full text linkThis study aims to formulate a strategic plan for the Information System (IS) and Information Technology (IT) at Politeknik Internasional Bali with the objective of enhancing the performance of business processes. The research employs a methodology that includes Ward and Peppard analysis, SWOT analysis, PEST analysis, Porter's Five Forces analysis, and Value Chain analysis. This comprehensive approach evaluates both the external and internal environments of the company, including the SI/TI company environment. The research provides strategic recommendations for the development of IS business strategies, IT strategies, and SI/TI management at Politeknik Internasional Bali. The findings from the SWOT Matrix Analysis reveal that Politeknik Internasional Bali is situated at coordinates (0.63, 1.74), indicating a strategic emphasis on SO (Strength-Opportunity) strategies. The suggested recommendations stemming from this analysis involve the design of information systems that actively support business processes, with a priority on systems located in the Strategic quadrant. The proposed IT Business strategies recommend the design of IT infrastructure architecture based on best practice principles, encompassing elements such as Availability, Scalability, Security, Serviceability, and Manageability. In addition to these recommendations, there is a proposal for organizational structural changes within Politeknik Internasional Bali, including the establishment of a dedicated SI/TI division to reinforce SI/TI management strategies. Overall, these recommendations are geared towards enhancing the overall effectiveness and efficiency of SI/TI utilization at Politeknik Internasional Bali
Development of a YOLO-Based Artificial Intelligence (AI) System for Early Detection of Stunting Risk in Children in 3T Regions of North Sumatra Province
Full text linkStunting is a chronic nutritional problem that has long-term impacts on children’s physical growth, cognitive development, and future productivity. This condition remains a major challenge in the 3T regions (frontier, outermost, and disadvantaged areas) of North Sumatra Province due to limited healthcare personnel, lack of measurement facilities, and delays in early detection. This study aims to develop an artificial intelligence system integrating YOLOv8 and Random Forest to automatically and in real time detect stunting risk in children. The YOLOv8 model is utilized to detect the presence of a child and estimate height through visual image analysis, while the Random Forest algorithm classifies the risk level based on the Height-for-Age Z-score (HAZ) derived from anthropometric and demographic data. The dataset consists of 29 children from 3T regions, with training and testing splits used to evaluate model performance. The results show that the system achieved an accuracy of 97.8%, precision of 96.5%, recall of 95.9%, F1-score of 96.2%, and an area under the ROC curve (AUC) of 0.98. The system successfully detects children in real time, produces risk classifications consistent with manual measurements, and automatically documents examination data. The novelty of this research lies in the integration of YOLO for automatic height measurement and Random Forest for nutritional classification, which has not been applied in the 3T regional context. This system has the potential to serve as a digital tool for healthcare workers and posyandu cadres to accelerate child nutrition monitoring in an efficient, accurate, and well-documented manner
Analysis of Predicting the Number of Rejected Chips Using Random Forest at PT. Wahyu Kartumasindo Internasional
Full text linkManufacturing industries face significant challenges in maintaining consistent product quality, particularly in minimizing reject rates across production machines, as high reject levels not only increase operational costs but also reduce overall efficiency and competitiveness. This study aims to develop a predictive approach using the Random Forest algorithm to forecast monthly chip rejects across different production machines, with historical reject data consisting of 1,820 records from June 2023 to September 2024 analyzed based on four primary reject categories and five production machines (DCL1, DCL2, CMI200, CMI200+, and YMJ400). The Random Forest model was applied to classify and predict reject patterns, and its performance was evaluated based on prediction accuracy and error rates, showing that the algorithm is effective in predicting reject counts with an absolute error of 0.640 ± 0.183, especially for lower reject values under 300, although accuracy decreases when handling higher reject levels above 500. Machine-level analysis further reveals that DCL1 and DCL2 consistently contribute the highest reject counts with high variability, while CMI200 and CMI200+ demonstrate stable performance with most rejects below 300, and YMJ400 generally records lower rejects but occasionally exhibits spikes, suggesting inconsistent performance. In conclusion, the Random Forest model provides a reliable predictive framework for monitoring reject trends, identifying DCL1 and DCL2 as priority targets for improvement, and supporting proactive maintenance strategies to enhance overall production quality
Sentiment Analysis of Skincare Products Using Lexicon and Multinomial Naive Bayes on The Sociolla Website
Full text linkGlobal warming has triggered extreme weather that negatively affects skin health, including damage, premature aging, and increased risk of skin cancer, prompting the use of skincare products. E-commerce platforms like Sociolla simplify skincare purchases, but the abundance of choices and varying skin reactions make product selection challenging. This study aims to assist consumers in making smarter purchase decisions by analyzing user reviews using sentiment analysis with a lexicon-based approach and the Multinomial Naive Bayes algorithm to classify reviews as positive or negative. The process includes data collection, text preprocessing, model development, and performance evaluation. The results show that this method achieved an accuracy of 80,64%, demonstrating its effectiveness in helping consumers filter reviews and select appropriate skincare products
Does Implementing Cryptography in Financial Risk Management Systems Reduce Data Security Risks – Literature Study
Full text link
ABSTRACT
This study investigates the use of cryptography in financial risk management systems to determine how well it mitigates data security risks. A key issue raised is the increasing threat to the integrity and privacy of financial data in the digital age, which requires more robust and flexible protection mechanisms. The objective is to determine the extent to which cryptographic techniques can enhance financial risk management systems and mitigate the possibility of data leakage and manipulation. The approach used is a literature review of various academic journals, scientific publications, and industry reports that discuss the integration of cryptography in the financial and information security domains. The study's findings indicate that cryptographic algorithms, such as AES, RSA, and blockchain-based encryption, can increase system resilience against cyberattacks while enhancing audit trails and access control. The implication of these findings is that the use of cryptography not only enhances data security but also increases stakeholder confidence in digital financial systems. To address the increasingly complex challenges of data security, this study suggests the creation of a set of cryptography policies and implementation standards integrated within a financial risk management framework. The analysis shows that cryptography plays a crucial role in maintaining the confidentiality, integrity, and authentication of financial data and can strengthen risk control systems against data leaks and manipulation. However, there is a gap in the literature regarding the integration of cryptography with a comprehensive risk management framework, as well as a lack of comparative evaluation of the effectiveness of various cryptographic techniques in the context of financial operations.
Keywords: Blockchain; data security; cryptography; digital financial system; encryptio
Integrating AHP and TBATS for Infectious Disease Prioritization and Forecasting in East Java
Full text linkAgrarian regions like East Java province face complex public health challenges. Some cases are caused by the interaction between social factors, and others by agribusiness factors. An integrative approach is needed to understand the dynamics of disease cases. This study aims to analyse the disease with the highest number of cases and project case trends in East Java using an integrated quantitative approach. Using methods such as the Analytic Hierarchy Process (AHP) to determine disease weights, the TBATS model is used to project case trends through 2028. Standardised multiple regression models were used to assess the influence of social factors (population density, poverty) and agribusiness (rice harvest area, agricultural labour). The data used are secondary time-series data from 2013 to 2023 obtained from BPS, the Health Department, and BMKG. The AHP results show diarrhoea as the disease with the highest weight (0.494), followed by pneumonia (0.112), tuberculosis (0.090), malaria (0.051), and dengue fever (0.049). The TBATS projection indicates medium-term fluctuations with the potential for an increase in dengue fever cases. Meanwhile, the regression results show that people in the agricultural sector are at increased risk of malaria (p = 0.037), while other variables have an influence but are not significant. Therefore, integrating health, social, and agribusiness data is an urgent need. And it can be used for early disease warning systems and more precise public health policy strengthening
IoT-Based Smart Water Quality Monitoring System for Early Detection of Water Pollution in Batam City
Full text linkWater pollution poses a significant threat to public health, particularly in rapidly developing urban areas such as Batam City, where domestic and industrial activities continue to increase. This study aims to analyse and monitor the quality of household tap water in Batam City over a 30-day period using an Internet of Things (IoT)-based smart water quality monitoring system. The research focuses on two key parameters, namely Total Dissolved Solids (TDS) and water temperature, which serve as primary indicators of water purity. Data were collected daily through a TDS sensor and a DS18B20 digital temperature sensor integrated into an IoT platform for continuous monitoring and real-time data acquisition. The results revealed that the water temperature ranged between 28–29 °C, indicating normal conditions for tropical regions and conforming to clean water standards. The TDS values varied from 310 to 355 ppm, remaining below the World Health Organization (WHO) safety limit of 500 ppm. Although slight fluctuations in TDS levels were observed during the observation period, no readings exceeded the acceptable threshold. These findings suggest that household tap water in Batam City is still safe for consumption and daily use. The study concludes that the application of IoT-based monitoring systems offers an effective approach for real-time water quality supervision and recommends regular monitoring along with the use of filtration devices to ensure long-term water safety and sustainabilit
The Application of the FMADM Electre Algorithm in Diagnosing the Level of Drug Addiction in Adolescents
Full text linkDrug abuse among adolescents was difficult to identify early without official examinations, while manual methods were often inaccurate. The process of determining rehabilitation also faced challenges due to the lack of technology-based support systems capable of effectively analyzing the level of addiction and type of drug used, resulting in rehabilitation that was often not well-targeted. To address this issue, the algorithm was utilized to diagnose drug addiction in adolescents by providing scores or rankings indicating addiction levels: scores of 1 and 2 represented mild addiction, 3 and 4 indicated moderate addiction, and 5 or higher represented severe addiction. The FMADM-ELECTRE algorithm recommended various types of rehabilitation actions for recovery. It offered precise evaluation ranges and scores, simplifying the classification and determination of appropriate detoxification measures for each type of drug-addicted adolescent. This system classified three levels of drug addiction among adolescents, corresponding to three stages of rehabilitation for drug addicts: non-medical (social) rehabilitation, medical rehabilitation (detoxification), and aftercare (post-rehabilitation). Additionally, the web-based support system was designed to be accessible across various devices, including laptops, computers, tablets, and smartphones, facilitating quicker and more efficient decision-making for relevant institutions. This approach also integrated multi-criteria methods to ensure fairness and accuracy in analysis, supporting a comprehensive rehabilitation process