Optimized Three Deep Learning Models Based-PSO Hyperparameters for Beijing PM2.5 Prediction

Pranolo, Andri; Mao, Yingchi; Wibawa, Aji Prasetya; Utama, Agung Bella Putra; Dwiyanto, Felix Andika

doi:10.17977/um018v5i12022p53-66

Cited by 9 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It first needs to be slightly tuned for the learning rate. It is also an easy strategy to use and is not affected by the diagonal scaling of gradients [33]. It requires less memory and is highly computationally efficient.…”

Section: F Adam Optimizationmentioning

confidence: 99%

Comparison of Adam Optimization and RMS prop in Minangkabau-Indonesian Bidirectional Translation with Neural Machine Translation

Ahda,

Wibawa,

Dwi Prasetya

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Language is a tool humans use to establish communication. Still, the language used is one language and between regions or nations with their languages. Indonesia is a country that has a diversity of second languages and is the fourth most populous country in the world. It is recorded that Indonesia has nearly 800 regional languages, but research activities in natural language processing are still lacking. Minangkabau is an endangered language spoken by the Minangkabau people in Indonesia's West Sumatra province. According to UNESCO, the Minangkabau language is listed as a language that is "definitely endangered," with only around 5 million speakers worldwide. This study uses neural machine translation (NMT) to create a formula based on this information. Neural machine translation, in contrast to conventional statistical machine translation, intends to build a single neural network that can be built up to achieve the best performance. Because it can simultaneously hold memory for a long time, comprehend complicated relationships in data, and provide information that is very important in determining the outcome of translation, LSTM is one of the most powerful machine-learning techniques for translating languages. The BLUE score is utilized in the NMT evaluation. The test results use 520 Minangkabau sentences, conducting tests based on the number of epochs ranging from 100-1000, resulting in optimization using Adam being better than optimization RMSprop. This is evidenced by the results of the best BLUE-1 score of 0.997816 using 1000 epochs.

show abstract

Section: F Adam Optimizationmentioning

confidence: 99%

Comparison of Adam Optimization and RMS prop in Minangkabau-Indonesian Bidirectional Translation with Neural Machine Translation

Ahda,

Wibawa,

Dwi Prasetya

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…Following Fig. 1, forecasting methods can be grouped into several categories: traditional statistical methods [24], [25], Machine Learning (ML) methods [26], [27], and Deep Learning (DL) [28], [29]. A more complete explanation of these categories is in the next sub-chapter according to each category.…”

Section: Fig 1 Basic Components Of Forecastingmentioning

confidence: 99%

Forecasting learning in electrical engineering and informatics: An ontological approach

Utama,

Patmanthara,

Wibawa

et al. 2023

IJELE

View full text Add to dashboard Cite

This research explores the vital role of ontology in learning forecasting in electrical engineering and informatics. As formally defined models of knowledge, ontologies are critical in organizing concepts for predictive learning. More than just an inquiry, our research reveals complex interconnections centered on Internet of Things (IoT) design, the semantic web, and knowledge modeling. Applications demonstrate the practical significance of ontologies in fostering intelligent connections, advancing information production, and improving interactions between computers, devices, and humans. This research introduces a comprehensive forecasting learning ontology to highlight the importance of ontologies in education, scientific inquiry, and developing systems for predictive analysis. Ontologies provide a structured framework for understanding the essence of predictive learning, encompassing key elements such as ideas, terminology, methodology, algorithms, data preprocessing, assessment, validation, data sources, application environments, interactions with technology, and learning processes. Emphasizing ontologies as indispensable instruments that drive technological development, our work underscores structured representation, semantic interoperability, and knowledge integration. In summary, this research improves the understanding of ontologies in forecasting by explaining practical applications and revealing new perspectives. Its unique contribution lies in its specific applications and natural consequences, laying the foundation for the future progress of ontology and learning forecasting, especially in educational contexts.

show abstract

“…ANN can be applied in some commercial cases, such as in the manufacturing industry, an oil company, trade, agriculture, insurance, electronics, computer, robotics, and even the medical sector [3], [6]. ANN also can be applied in linear or nonlinear, parametric or non-parametric, and continuous datasets [7]- [9]. Some classes of data mining techniques include anomaly detection, learning of rule association, clustering, classification, regression, and summarization.…”

Section: Introductionmentioning

confidence: 99%

Leveraging hybrid ANN–AHP to optimize cement industry average inventory levels

Fradinata,

Noor,

Kesuma

et al. 2024

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

In recent years, inventory has been critical due to the production cost and overstock risk related to the expiration date and the fluctuation price risk. This study's minimization of overstock and price fluctuation in the warehouse used a hybridized artificial neural network (ANN) and analytical hierarchy process (AHP) to produce an optimum model. The variables, such as average demand, reorder point, order quantity, factor service level, safety stock, and average inventory level, were used to obtain the optimal condition of the average inventory levels to maximize the profit. Then, the type of inventory system that guarantees the minimum risks in managing the inventory would be selected. The result shows that the data has a mean of 39.2 units, and the standard deviation (SD) was 12.9. This means that the order quantity is 20.2 units, the average inventory level is 57.3, and the average demand is 39. These conditions used the factor z, which is 97% service level. This study concludes that the optimum average inventory level is 91 units, the order quantity is 11 units with the maximum average profit is $1098, and the peak fluctuation condition maximum profit is $1463 when the average inventory level is 7.3, and the inventory policy system used to minimize the risk is the continuous review policy type. The study could be beneficial to reduce production costs and enhance overall profitability and operational efficiency in the sector by mitigating the risks associated with excessive inventory and price volatility while also minimizing the potential for expired inventory.

show abstract

Optimized Three Deep Learning Models Based-PSO Hyperparameters for Beijing PM2.5 Prediction

Cited by 9 publications

References 40 publications

Comparison of Adam Optimization and RMS prop in Minangkabau-Indonesian Bidirectional Translation with Neural Machine Translation

Comparison of Adam Optimization and RMS prop in Minangkabau-Indonesian Bidirectional Translation with Neural Machine Translation

Forecasting learning in electrical engineering and informatics: An ontological approach

Leveraging hybrid ANN–AHP to optimize cement industry average inventory levels

Contact Info

Product

Resources

About