Search published articles


Showing 2 results for Mewma
Monitoring Multinomial Logit Profiles via Log-Linear Models (Quality Engineering Conference Paper)
Rassoul Noorossana, Abbas Saghaei, Hamidreza Izadbakhsh, Omid Aghababaei,
Volume 24, Issue 2 (6-2013)
Abstract
In certain statistical process control applications, quality of a process or product can be characterized by a function commonly referred to as profile. Some of the potential applications of profile monitoring are cases where quality characteristic of interest is modelled using binary,multinomial or ordinal variables. In this paper, profiles with multinomial response are studied. For this purpose, multinomial logit regression (MLR) is considered as the basis.Then, the MLR is converted to Poisson GLM with log link. Two methods including Multivariate exponentially weighted moving average (MEWMA) statistics, and Likelihood ratio test (LRT) statistics are proposed to monitor MLR profiles in phase II. Performances of these three methods are evaluated by average run length criterion (ARL). A case study from alloy fasteners manufacturing process is used to illustrate the implementation of the proposed approach. Results indicate satisfactory performance for the proposed method.
The SCAN Method to Monitor Cryptocurrency Transactions
Fatemeh Elhambakhsh, Kamyar Sabri-Laghaie,
Volume 33, Issue 1 (3-2022)
Abstract
The fourth industrial revolution has changed our lives by enabling everyone to be interconnected virtually. A trustworthy system is required to secure large volume of stored data in IoT-based devices. Blockchain technology has led to transfer and to save data in a safe way. With this in mind, the blockchain-based cryptocurrencies have gained quite a bit of popularity because of their potential for financial transactions. In this regard, monitoring transactions network is very fruitful to find users’ abnormal behaviors. In this research, a novel procedure is used to monitor blockchain cryptocurrency transactions network. To do so, a random, binary graph model is used to simulate the transactions between users, and a SCAN method is used to detect the abnormal behaviors in the simulated model. Also, a multivariate exponentially weighted moving average (MEWMA) control chart is used to monitor centrality measures. The probability of signal is used to assess the performance of the SCAN method and that of the MEWMA control chart in distinguishing abnormalities. Then, the procedure is adopted to a Bitcoin transactions dataset.
Page 1 from 1