Pattern Recognition Unit Research Articles

Inkjet-printed MOS-based MEMS sensor array combined with one-dimensional convolutional neural network algorithm for identifying indoor harmful gases

To achieve a highly accurate and efficient analysis of mixed gases, it is crucial to develop an electronic nose system with high sensitivity of gas sensors and low data processing complexity. In this study, the metal oxide semiconductor (MOS) based micro-electromechanical system (MEMS) gas sensor array was prepared by inkjet printing sensing materials onto a micro-hotplate. The pattern recognition unit employed a one-dimensional convolutional neural network (1D-CNN) to identify 7 types of gases. While the optimal traditional machine learning algorithm achieved an 80% recognition accuracy, the 1D-CNN can achieve 99.8%. Furthermore, the impact of varying time series input lengths on the model accuracy was investigated, pinpointing an optimal sampling time of 15 s. This work showed that integrating the MEMS sensor array with the 1D-CNN algorithm might offer a promising approach for intricate gas classification and identification.

Study of fish species discrimination via electronic nose

Fish freshness is a critical issue in determining fish quality. Since fish freshness changes according to the fish species, fish species has to be identified before examining the freshness. So far, fish species have been distinguished through different methods such as image processing. In this paper, an electronic nose has been used to distinguish between different species of fish. Thus, both freshness and species of fish will be determined just using a single, low cost device. The aim of this study is to distinguish between three different species of fish – horse mackerel, anchovy and whiting – by using an electronic nose composed of 8 different metal oxide gas sensors. In order to distinguish between the species of fish, a whole new method, which is not applied to this kind of data previously, is used and proposed for use in the pattern recognition unit of the electronic nose. It is examined in three parts such as signal pre-processing, feature extraction and classification. In the pre-processing stage, to reduce the negative effect of sensor drift, a new method is applied to the raw signal in addition to the well-known baseline manipulation method. In the feature extraction part, the sub-sampling method which is not frequently used is applied to the pre-processed signal. The extracted features are used in the classification part. The structure of the proposed classification algorithm is based on binary decision tree structure. The binary decision tree structure is composed of nodes. In every node of the decision tree structure, the feature spaces or classification algorithm can be changed according to the problem. Classification results demonstrate the effectiveness of the presented models. The overall accuracy of the identification of fish species achieved with the proposed methods is 96.18%. The performance of the proposed method is also compared to conventional methods such as Naïve Bayes, k-Nearest Neighbor and Linear Discriminant Analysis. The successes of these classifiers are 84.73, 80 and 82.4, respectively.

Elements of a cybernetic epistemology

PurposeThe purpose of this paper is to analyze how pattern recognition can contribute to the behavioral options of a goal‐oriented system.Design/methodology/approachA functional approach is used to develop the necessary cybernetic structures of a pattern recognition unit that can store observations as new standards for pattern matching by itself and can later apply them to recognize patterns in incoming sensor data.FindingsCombining such a structure for pattern recognition with a feedback system shows that the resulting system can only deal with known patterns. To deal with novel patterns this structure has to be added to an adaptive system that can develop system‐specific behavior. Such a system has to able to initiate a trial and error process to test new behavior towards new patterns and to evaluate its effect on the highest, existential goal‐values of the system.Practical implicationsA system with a pattern recognition unit that can set new standards for pattern matching by itself is identified as the point of departure where not‐programmable and unpredictable individual behavior starts. Dealing with newly‐recognized pattern requires individual behavioral solutions and a system‐specific evaluation of the achieved results in relation to the highest goal‐values of the system. Here internal “emotional” criteria to select behavior emerge as a cybernetic necessity.Originality/valueThe paper is the third in a series of three on a cybernetic theory distinguishing system capable of pre‐programmed adaptation, system‐specific adaptation and learning. It determines the cybernetic starting point of individual psychology.

Evolutionary RBF classifier for polarimetric SAR images

In this paper, a robust radial basis function (RBF) network based classifier is proposed for polarimetric synthetic aperture radar (SAR) images. The proposed feature extraction process utilizes the covariance matrix elements, the H/α/A decomposition based features combined with the backscattering power (span), and the gray level co-occurrence matrix (GLCM) based texture features, which are projected onto a lower dimensional feature space using principal components analysis. For the classifier training, both conventional backpropagation (BP) and multidimensional particle swarm optimization (MD-PSO) based dynamic clustering are explored. By combining complete polarimetric covariance matrix and eigenvalue decomposition based pixel values with textural information (contrast, correlation, energy, and homogeneity) in the feature set, and employing automated evolutionary RBF classifier for the pattern recognition unit, the overall classification performance is shown to be significantly improved. An experimental study is performed using the fully polarimetric San Francisco Bay and Flevoland data sets acquired by the NASA/Jet Propulsion Laboratory Airborne SAR (AIRSAR) at L-band to evaluate the performance of the proposed classifier. Classification results (in terms of confusion matrix, overall accuracy and classification map) compared with the major state of the art algorithms demonstrate the effectiveness of the proposed RBF network classifier.

Automatic nuclei segmentation and spatial FISH analysis for cancer detection.

Spatial analysis of gene localization using fluorescent in-situ hybridization (FISH) labeling is potentially a new method for early cancer detection. Current methodology relies heavily upon accurate segmentation of cell nuclei and FISH signals in tissue sections. While automatic FISH signal detection is a relatively simpler task, accurate nuclei segmentation is still a manual process which is fairly time consuming and subjective. Hence to use the methodology as a clinical application, it is necessary to automate all the steps involved in the process of spatial FISH signal analysis using fast, robust and accurate image processing techniques. In this work, we describe an intelligent framework for analyzing the FISH signals by coupling hybrid nuclei segmentation algorithm with pattern recognition algorithms to automatically identify well segmented nuclei. Automatic spatial statistical analysis of the FISH spots was carried out on the output from the image processing and pattern recognition unit. Results are encouraging and show that the method could evolve into a full fledged clinical application for cancer detection.

A Generic and Robust System for Automated Patient-Specific Classification of ECG Signals

This paper presents a generic and patient-specific classification system designed for robust and accurate detection of ECG heartbeat patterns. The proposed feature extraction process utilizes morphological wavelet transform features, which are projected onto a lower dimensional feature space using principal component analysis, and temporal features from the ECG data. For the pattern recognition unit, feedforward and fully connected artificial neural networks, which are optimally designed for each patient by the proposed multidimensional particle swarm optimization technique, are employed. By using relatively small common and patient-specific training data, the proposed classification system can adapt to significant interpatient variations in ECG patterns by training the optimal network structure, and thus, achieves higher accuracy over larger datasets. The classification experiments over a benchmark database demonstrate that the proposed system achieves such average accuracies and sensitivities better than most of the current state-of-the-art algorithms for detection of ventricular ectopic beats (VEBs) and supra-VEBs (SVEBs). Over the entire database, the average accuracy-sensitivity performances of the proposed system for VEB and SVEB detections are 98.3%-84.6% and 97.4%-63.5%, respectively. Finally, due to its parameter-invariant nature, the proposed system is highly generic, and thus, applicable to any ECG dataset.