Today for the expedition of the identification and timely correction of process deviations, it is necessary to use advanced techniques to minimize the costs of production of defective products. In this way control charts as one of the important tools for the statistical process control in combination with modern tools such as artificial neural networks have been used. The artificial neural networks were used to recognize the pattern in control charts in several research. Two procedures were used based on the raw data and feature for training and application of neural network. This paper presented new statistical features besides the investigation of their efficiency by application of a neural network. The simulation results demonstrated the positive effect of the presented statistical feature on neural network performance.

Structural health monitoring is an economical and reliable strategy for infrastructure condition assessment. In recent years, researchers have tried to propose algorithms based on statistical pattern recognition techniques. Studies show these algorithms can be successfully used to detect structural damage. Variability of operational and ambient conditions during data acquisition should be considered as an important factor in applying statistical pattern recognition methods in practical applications. This paper studies the efficiency of statistical pattern recognition methods on the damage detection of structures under various operational and ambient conditions. The data is obtained from an experimental study on an eight degrees of freedom mass spring system. Ambient vibration is applied to the mass spring system using random excitation. In order to simulate various ambient conditions, the amplitude level of the input force has been varied. By applying the statistical pattern recognition methods, the ability of these methods to damage detection under various ambient conditions is discussed. Two common approaches of statistical pattern recognition are considered. These approaches are autoregressive model accompanied with using control chart and Mahalanobis distance for outlier analysis. Results show the importance of considering the statistical pattern recognition methods for structural damage detection under various operational and ambient conditions.

Background: Rheumatoid arthritis (RA) is a chronic, systematic inflammatory disorder that may affect many tissues and organs, but principally attacks synovial joints and it is a common rheumatic disease with many subtypes. Nuclear Magnetic resonance (1H NMR) spectrometers with high sensitivity, resolution and dynamic range has permitted the rapid, simultaneous investigation of complex mixtures of endogenous or exogenous components present in biological materials. Metabonomics is the systematic study of chemical finger print resulted from cell reactions and could be used as a new biomarker for early disease diagnosis. In the present investigation, we studied serum metabolic profile in rheumatoid arthritis (RA) in order to find out the metabolic finger print pattern of the disease.Materials and methods: In our metabonomics study serum samples were collected from 16 patients with active RA, and from equal number of healthy subjects. They were evaluated during a one-year follow-up with the assessment of disease activity and 1H NMR spectroscopy of sera samples. In all the cases, the presence of active rheumatoid arthritis was shown by an increase in the T1 values of the synovium of the joints. We specified and classified all metabolites using PCA, PLSDA chemometrics methods. Chenomx (Trail Version) and ProMetab codes in Matlab software environments were used for our data analysis. Results were compared with the NMR metabolite data bank (www.metabolomics.ca). Anti-CCP, ANA and urea were also analyzed by ElISA and colorimetric methods respectively.Results: The most changes identified in this study were in the biosynthesis pathways of steroid hormones, biotin, fatty acids, amino acids (Leucine, Valin and isoleucine) and also linoleic acid.Conclusion: In rheumatoid arthritis disease, the activation of the immune system consumes larg amounts of energy. The main donor of free energy in cells is ATP, which is generated by both glycolysis and oxidative phosphorylation. Changes in amino acids and free fatty acids biosynthesis pathways confirm the high energy utilization. In this disease, the increase in free fatty acid metabolism leads to production of Acetyl CoA and ketone bodies. Since there are many diseases subtype in rheumatoid arthritis, more sensitive diagnostic method is required. The result of our investigation suggests that metabolome profiling method could be used as a new biomarker for early diagnosis of rheumatoid arthritis disease.

This paper investigates a category-based statistical language model for Persian continuous speech recognition. The language models are based on variable-length category-based n-grams. Instead of finding patterns among individual words, a language model may be designed to discover relationships between word categories. In this research, this has been accomplished in 3 steps; clustering words into groups, exploitation of the statistical language model employing tree data structure and its application to the recognition system. The most important advantage of this model has found to be its ability to return to correct path in situations where ordinary statistical modeling does not allow it.

In industrial rotatory machines, different forces in rotor bearings are generated due to various impaired mechanical sources, namely bearing misalignment and nonhomogeneous mass distribution (unbalance). By precisely analyzing and diagnosing the produced patterns of bearing forces, one can determine the unbalance parameters such as quantities of masses, their distance from the rotational axis, and characteristics of corresponding parallel planes. Consequently, it will be possible to formulate pragmatic protocols according to which the maintenance engineers of rotatory systems will pinpoint properties of problematic imbalance masses and then straightforwardly balance them. In the procedure of conducting this research, several exemplary imbalance masses are deployed on a rotatory mechanical shaft and the equations of motion and forces in perfectly aligned rigid bearings are extracted. Then, by applying a neural network-oriented system the patterns of bearing forces are recognized and the characteristics of the nominal masses including magnitudes, distances from the rotational axis, angles as well as the unbalance type are determined. The accuracy of predicting 8 variables of balancing masses was 41% and after eliminating the redundant overlaps from principal components, the accuracy of predicted 5 variables of balancing masses significantly increased to 95%. Also, by implementing another comprehensive neural network system, it was shown that by exerting two separate balancing masses, the applicability of this method in balancing any faulty systems with dynamic unbalance is possible.

The objective of this study was to assess the relationships between physicochemical and microbiological properties of raw milk and the use of multivariate statistical analysis such as principal component analysis (PCA), hierarchical cluster analysis (HCA) and stepwise discriminant analysis (SDA) for pattern recognition and classification it. In this study, 48 raw milk samples were collected from some dairy herds of Mashhad. Samples were analyzed for the microbiological and physicochemical properties. PCA, HCA and SDA were applied to estimate the usefulness of the physicochemical and microbiological parameters for the differentiation and classification of raw milk using. The results of PCA shown the seven principal components explained 93.65% of total system variance. The PCA method permits a good classification between raw milk samples on the basis of the first three PCs. HCA classified physicochemical and microbiological properties of raw milk into three main groups that confirmed the correlation between the studied variables obtained by PCA. Using SDA it was determined which variables best classified the raw milk samples according to their quality. Finally, the classification functions allowed the correct classification of 91.7% of the raw milk samples. Due to the direct effect of raw milk quality on dairy products quality and consumer health, the quality of raw milk has special importance in the dairy industry. Therefore, classification of raw milk based on the quality characteristics will help to determine the price of raw milk and to produce high quality dairy products.