Demand Forecasting of Anti-Aircraft Missile Spare Parts Using Neural Network
12 Jun 2019-pp 572-578
TL;DR: In this article, the authors used the dataset used is that of Vietnam War Bombing Operations and the proposed modeling involved- the aircraft name along with its unit of issue, how many spare parts are exhausted and how many are remaining.
Abstract: One of the major hurdles today is maintaining the right amount of stock keeping units since it may lead to under utilization or over utilization. Spare parts play a very vital role in any inventory or industrial companies. The importance of spare parts can be identified by their sizeable amount and their impact on business operations. One of the major industries today is aircraft industry which includes some of the most fundamental factors like increasing terrorist activities across the world, rising request for technologically robust anti-aircraft missiles and the growing defense funds of emerging countries. Inventory needs to keep an eye on these activities so as to estimate the future consumption. In this study, the dataset used is that of Vietnam War Bombing Operations .The proposed modeling involved- the aircraft name along with its unit of issue, how many spare parts are exhausted and how many are remaining. This helps in finding out the quantity required for demanding the exhausted spare parts by maintaining the budget .The trial about Multi-layer Perceptron (MLP) and XGBoost demonstrates effectiveness in terms of time and memory which is the ultimate aim to improve the precision in terms of demand accuracy.
Citations
More filters
••
TL;DR: In this paper , a reliable and ensemble data mining approach with considering managerial characteristics (e.g., repair ability and the irregularity of maintenance such as MTBF and MTTR) along with their history of consumption was proposed to predict the amount of spare parts and the time of the following order.
1 citations
•
20 Feb 2020
TL;DR: In this article, an inventory control system is configured to perform operations including generating an initial demand matrix and generating a plurality of synthetic demand matrices, identifying sparse demand vectors in the synthetic demand matrix, where each sparse demand vector represents synthetic demand that satisfies a sparse demand criteria.
Abstract: An inventory control system is configured to perform operations including generating an initial demand matrix and generating a plurality of synthetic demand matrices. The operations also include identifying sparse demand vectors in the synthetic demand matrices, where each sparse demand vector represents synthetic demand that satisfies a sparse demand criteria. The operations also include modifying synthetic demand values based on the sparse demand vectors to generate filtered synthetic demand matrices. The operations include generating estimated demand for a target period for each inventory item based on the filtered synthetic demand matrices and the initial demand matrix and comparing the estimated demand to inventory data to determine whether one or more inventory items should be acquired. The operations include generating and sending a demand signal to cause the one or more inventory items to be acquired.
References
More filters
•
01 Jan 1983
TL;DR: Reading is a need and a hobby at once and this condition is the on that will make you feel that you must read.
Abstract: Some people may be laughing when looking at you reading in your spare time. Some may be admired of you. And some may want be like you who have reading hobby. What about your own feel? Have you felt right? Reading is a need and a hobby at once. This condition is the on that will make you feel that you must read. If you know are looking for the book enPDFd introduction to modern information retrieval as the choice of reading, you can find here.
12,059 citations
••
TL;DR: It is suggested that the random forest classifier performs equally well to SVMs in terms of classification accuracy and training time and the number of user‐defined parameters required byrandom forest classifiers is less than the number required for SVMs and easier to define.
Abstract: Growing an ensemble of decision trees and allowing them to vote for the most popular class produced a significant increase in classification accuracy for land cover classification. The objective of this study is to present results obtained with the random forest classifier and to compare its performance with the support vector machines (SVMs) in terms of classification accuracy, training time and user defined parameters. Landsat Enhanced Thematic Mapper Plus (ETM+) data of an area in the UK with seven different land covers were used. Results from this study suggest that the random forest classifier performs equally well to SVMs in terms of classification accuracy and training time. This study also concludes that the number of user‐defined parameters required by random forest classifiers is less than the number required for SVMs and easier to define.
2,255 citations
"Demand Forecasting of Anti-Aircraft..." refers background in this paper
...[5], focuses on association of decision trees with support vector...
[...]
•
08 Jul 1997
TL;DR: This work proposes an approach that utilizes the hierarchical topic structure to decompose the classification task into a set of simpler problems, one at each node in the classification tree, which can be solved accurately by focusing only on a very small set of features, those relevant to the task at hand.
Abstract: The proliferation of topic hierarchies for text documents has resulted in a need for tools that automatically classify new documents within such hierarchies. One can use existing classifiers by ignoring the hierarchical structure, treating the topics as separate classes. Unfortunately, in the context of text categorization, we are faced with a large number of classes and a huge number of relevant features needed to distinguish between them. Consequently, we are restricted to using only very simple classifiers, both because of computational cost and the tendency of complex models to overfit. We propose an approach that utilizes the hierarchical topic structure to decompose the classification task into a set of simpler problems, one at each node in the classification tree. As we show, each of these smaller problems can be solved accurately by focusing only on a very small set of features, those relevant to the task at hand. This set of relevant features varies widely throughout the hierarchy, so that, while the overall relevant feature set may be large, each classifier only examines a small subset. The use of reduced feature sets allows us to utilize more complex (probabilistic) models, without encountering the computational and robustness difficulties described above.
1,039 citations
••
TL;DR: This paper studies the phenomenon of financial distress for 107 Chinese companies that received the label ‘special treatment’ from 2001 to 2008 to discover that financial indicators play an important role in prediction of deterioration in profitability.
304 citations
"Demand Forecasting of Anti-Aircraft..." refers methods in this paper
...Geng et al.[18], worked actively on data mining methods for developing models with respect to forecasting the financial misery of Chinese companies that are based on 31financial indicators....
[...]
...Geng et al.[18], worked actively on data mining methods for developing models with respect to forecasting the financial misery of Chinese...
[...]
••
01 Oct 2006TL;DR: A multi-agent system to simulate a supply chain, where agents are coordinated to control inventory and minimize the total cost of a SC by sharing information and forecasting knowledge is developed.
Abstract: Supply chain management (SCM) is an emerging field that has commanded attention and support from the industrial community. Demand forecast taking inventory into consideration is an important issue in SCM. There are many diverse inventory systems, in theory or practice, which are operated by entities (companies) in a supply chain. In order to increase supply chain effectiveness, minimize total cost, and reduce the bullwhip effect, integration and coordination of these different systems in the supply chain (SC) are required using information technology and effective communication. The paper develops a multi-agent system to simulate a supply chain, where agents operate these entities with different inventory systems. Agents are coordinated to control inventory and minimize the total cost of a SC by sharing information and forecasting knowledge. The demand is forecasted with a genetic algorithm (GA) and the ordering quantity is offered at each echelon incorporating the perspective of "systems thinking". By using this agent-based system, the results show that total cost decreases and the ordering variation curve becomes smooth.
142 citations