Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Journal of Applied Research In Computer Science and Information Systems

Performance Assessment of ARIMA and LSTM Models in Prediction Using Root Mean Square Error (RMSE) Andiani, Andiani; Simanjuntak, Yoel; Wiliani, Ninuk
Journal of Applied Research In Computer Science and Information Systems Vol. 2 No. 1 (2024): June 2024
Publisher : PT. BERBAGI TEKNOLOGI SEMESTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61098/jarcis.v2i1.181

Abstract

Cryptocurrency is a digital financial asset that serves as a medium of exchange, with its ownership guaranteed using decentralized cryptographic technology, and it has become a growing investment tool. Solana is one of the highly sought-after Cryptocurrencies by investors. The market price of Solana exhibits highly volatile movements, which are considered risky for investment purposes, as it offers both high potential profits and losses. In this regard, time series data prediction models are used to analyze and forecast the price movements of Solana. By comparing the performance of ARIMA and LSTM models in predicting the closing price of Solana using RMSE as a testing metric, the aim is to determine the efficiency level of both ARIMA and LSTM models. The research results show that the ARIMA model with an order of (2,1,3) achieves an RMSE of 0.019 (1.9%) with an accuracy of 98.1%, while the LSTM model with a data training ratio of 70:30%, a batch size of 64, and 500 epochs has an RMSE of 0.075 (7.5%) with an accuracy of 92.5%. The conclusion drawn from the conducted experiments is that, in the case of using time series data samples from Solana, the ARIMA method demonstrates higher accuracy compared to the LSTM method.
K-Means Clustering for Identifying Traffic Accident Hotspots in Depok City Wahyono, Herry; Setiaji, Hari; Hartati, Tri; Wiliani, Ninuk
Journal of Applied Research In Computer Science and Information Systems Vol. 2 No. 1 (2024): June 2024
Publisher : PT. BERBAGI TEKNOLOGI SEMESTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61098/jarcis.v2i1.182

Abstract

This study applies the K-Means clustering algorithm to support decision-making processes related to identifying traffic accident-prone areas in Depok City over a three-year period (2020-2022). Secondary data was obtained from the Traffic Accident Unit of the Depok Metro Police, encompassing monthly traffic accident recapitulations for each district. The data underwent preprocessing steps, including integration and selection of relevant attributes. Using RapidMiner, the data was clustered into three distinct groups, with the optimal number of clusters determined by the Davies-Bouldin Index (DBI), which yielded a score of 0.896, indicating a satisfactory clustering result. The findings reveal that four districts—Beji, Cimanggis, Pancoran Mas, and Sukmajaya—are identified as high-risk areas for traffic accidents. These results are expected to assist local authorities in implementing targeted safety measures. The study demonstrates that the K-Means clustering method is a viable tool for analyzing traffic accident data and can significantly contribute to improving road safety in urban areas
Identifying Damage Types in Solar Panels Through Surface Image Analysis with Naive Bayes Wiliani, Ninuk; Abdul Rahman, Titik Khawa; Ramli, Suzaimah
Journal of Applied Research In Computer Science and Information Systems Vol. 2 No. 2 (2024): December 2024
Publisher : PT. BERBAGI TEKNOLOGI SEMESTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61098/jarcis.v2i2.200

Abstract

The growing utilization of solar panels as a renewable energy source requires efficient maintenance solutions to guarantee their best functioning. Identifying and categorizing faults on solar panel surfaces is essential for maintenance, as these defects considerably affect energy output and system efficiency. This study investigates the utilization of statistical feature extraction methods alongside Bernoulli Naive Bayes (BNB) and Gaussian Naive Bayes (GNB) algorithms to categorize different defect types, such as cracks, scratches, spots, and non-defective surfaces, through digital image analysis. Statistical criteria, including recall, specificity, and area under the curve (AUC), are employed to assess model performance. The findings indicate that the GNB algorithm surpasses BNB, with a mean average precision (mAP) of 39.83% with an 85:15 training-test ratio, whereas BNB reaches a maximum mAP of 29.25% at a 90:10 ratio. Nonetheless, both models demonstrate constraints in precision, as indicated by a total AUC of 0.644. This work illustrates the potential of statistical feature extraction approaches for defect classification, while emphasizing the necessity for future improvements to boost the efficacy of feature extraction and classification techniques in practical applications