A Combinatorial Deep Learning and Deep Prophet Memory Neural Network Method for Predicting Seasonal Product Consumption in Retail Supply Chains DOI
Ahmad Y. A. Bani Ahmad,

Mokshed Ali,

Arpit Namdev

et al.

Advances in business information systems and analytics book series, Journal Year: 2024, Volume and Issue: unknown, P. 311 - 340

Published: Sept. 20, 2024

One of the biggest problems in supply chain networks is demand forecasting. It was created to increase demand, profitability, and sales while maximizing stock efficiency cutting costs. To improve forecasting, historical data may be analyzed using a variety techniques, such as deep learning models, time series analysis, machine learning. This study develops hybrid approach prediction. paper used learning-based Deep Prophet memory neural network forecasting approach, which combined temporal, historical, trend, seasonal data, develop more accurate model. our knowledge, this first integrate prophet with long short-term (LSTM) for At first, obtained here, linear clipping normalization (LCDN) pre-processing. After that, bivariate wrapper forward elimination extract features. The Sequential Bayesian Inference Optimization (SBIO) choose specialized features from retrieved characteristics. Ultimately, items examined after Memory Neural Network (DPMNN) modified. Using M5 Forecasting Predict Future Sales datasets Python context, built system evaluated. Numerous exhaustive comparative trials show that suggested technique performs much better than state-of-the-art research.

Language: Английский

Emergent Applications of Organ-on-a-Chip (OOAC) Technologies With Artificial Vascular Networks in the 21st Century DOI
Ranjit Barua, Nirmalendu Biswas, Deepanjan Das

et al.

Advances in healthcare information systems and administration book series, Journal Year: 2024, Volume and Issue: unknown, P. 198 - 219

Published: Feb. 14, 2024

The organ-on-a-chip (OOAC) technology stands at the forefront of emergent technologies, representing a biomimetic configuration functional organs on microfluidic chip. This synergizes biomedical engineering, cell biology, and biomaterial to mimic microenvironment specific organs. It effectively replicates biomechanical biological soft tissue interfaces, enabling simulation organ functionality responses various stimuli, including drug reactions environmental effects. OOAC has vast implications for precision medicine defense strategies. In this chapter, authors delve into principles OOAC, exploring its role in creating physiological models discussing advantages, current challenges, prospects. examination is significant as it highlights transformative potential technologies 21st century contributes deeper understanding OOAC's applications advancing medical research.

Language: Английский

Citations

17
Effects of Genetic Counseling on Reducing Prenatal Stress and Autism Rates in the Asia-Pacific Region DOI

Yanhua Bi,

Kadir Uludağ

Advances in healthcare information systems and administration book series, Journal Year: 2024, Volume and Issue: unknown, P. 341 - 363

Published: Feb. 14, 2024

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by difficulties in social interaction, repetitive behaviors, and narrow interests. People with ASD often experience additional mental health issues such as depression anxiety. While genetics have long been considered significant factor the development of ASD, recent research indicates that interplay between genes environment crucial understanding its underlying causes. This chapter aims to discuss relationship prenatal stress characteristics countries within Asia-Pacific region. The findings indicate connection traits China, South Korea, Japan. Further investigation required fully comprehend specific mechanisms involved this relationship. Genetic consultation can provide insights into potential risk factors, genetic counseling, guidance on personalized interventions.

Language: Английский

Citations

15
A Combinatorial Deep Learning and Deep Prophet Memory Neural Network Method for Predicting Seasonal Product Consumption in Retail Supply Chains DOI
Ahmad Y. A. Bani Ahmad,

Mokshed Ali,

Arpit Namdev

et al.

Advances in business information systems and analytics book series, Journal Year: 2024, Volume and Issue: unknown, P. 311 - 340

Published: Sept. 20, 2024

One of the biggest problems in supply chain networks is demand forecasting. It was created to increase demand, profitability, and sales while maximizing stock efficiency cutting costs. To improve forecasting, historical data may be analyzed using a variety techniques, such as deep learning models, time series analysis, machine learning. This study develops hybrid approach prediction. paper used learning-based Deep Prophet memory neural network forecasting approach, which combined temporal, historical, trend, seasonal data, develop more accurate model. our knowledge, this first integrate prophet with long short-term (LSTM) for At first, obtained here, linear clipping normalization (LCDN) pre-processing. After that, bivariate wrapper forward elimination extract features. The Sequential Bayesian Inference Optimization (SBIO) choose specialized features from retrieved characteristics. Ultimately, items examined after Memory Neural Network (DPMNN) modified. Using M5 Forecasting Predict Future Sales datasets Python context, built system evaluated. Numerous exhaustive comparative trials show that suggested technique performs much better than state-of-the-art research.

Language: Английский

Citations

0