Implementation of Spatial Images Using Rough Set-Based Classification Techniques

This study presents the development of artificial neural network (ANN) and support vector machine (SVM) classification models for predicting the safety conditions of water in distribution pipes. The study was based on 504 monthly records of water quality parameters; pH, turbidity, color and bacteria counts taken from nine different locations across the water distribution network in the city of Alesund, Norway. The models predicted the safety conditions of the water samples in the pipes with 98% accuracy and 94% respectively during testing. The high accuracy achieved in the model results indicate that contamination events in distribution systems that result in unsafe values of the water quality parameters can be detected using these classification models. This can provide water utility managers with real time information about the safety conditions of treated water at different locations of distribution pipes before water reaches consumers.

The prediction of meteorological phenomena resulting from rainfall, is one of the most important elements of the minimization of the damages. Local meteorological radars works at regional base hence they cannot represent the parameters of precipitation. Because of insufficiency of the radar systems early detection, satellite images can be used to create decision systems. At this point firstly infrared satellite images will be classified and then comparative results will be discussed on experimental stage. In this work, we used Wavelet Transform applied to infrared satellite images to extract approximation coefficients. Size of these coefficients are reduced using Principal Component Analysis and classified through classification algorithms. Artificial Neural Network and Support Vector Machines are used for classification. As a result of the classification made with Artificial Neural Networks, we accomplished 84% prediction rate. With the classification of Support Vector Machines, we reached 93% prediction rate.

Nowadays, the Structural Building Health Damage Monitoring System (SBHDMS) is a crucial technology for predicting the civil building structures' health. SBHDMS contains abnormal changes in the buildings in terms of damage levels. Natural Disasters like Earthquakes, Floods, and cyclones affect the unusual changes in the buildings. If the building undergoes any natural disaster, the sensors capture the vibration data or change the buildings' structure. Due to the vibration data, these unusual changes can be analyzed. Here sensors or Machine Learning based Building Damage Prediction (MLBDP) are used for capturing and collecting the vibration data. This paper proposes a Novel Rough Set based Artificial Neural Network with Support Vector Machine (RAS) metaheuristic method. RAS method is used to predict the damaged building's vibration data levels captured by the sensors. For the feature reduction subset, we use one of the essential pre-processing method called the Rough set theory (RST) strategy. RAS has two contributions. The first one is the Support Vector Machine (SVM) classification method used for identifying the structures of the buildings. The artificial Neural Network (ANN) method used to predict the buildings' damage levels is the second contribution. The proposed method (RAS) is accurately predicting the conditions of the construction building structure and predicting the damage levels, without human intervention. Comparing the results states that the proposed method accuracy is better than SVM's classification methods, ANN. The prediction analysis depicts that the RAS method can effectively detect the damage levels.

The diagnosis of incipient fault is important for power transformer condition monitoring. Incipient faults are monitored by conventional and artificial intelligence based models. Key gases, percentage value of gases, and ratio of the Doernenburg, Roger, IEC methods are input variables to artificial intelligence models, which affects the accuracy of incipient fault diagnosis, so selection of the most influencing relevant input variable is an important research area. With this main objective, Waikato Environment for Knowledge Analysis software is applied to 360 simulated samples having different operating lives to find the most influencing input parameters for incipient fault diagnosis in the gene expression programming model. The Waikato Environment for Knowledge Analysis identifies%C2H2,%C2H4,%CH4, C2H6/C2H2, C2H2/C2H4, CH4/H2, C2H4/C2H6, and C2H2/CH4 as the most relevant input variables in incipient fault diagnosis, and it is used for fault diagnosis using different artificial intelligence methods, i.e., artificial neural networks, fuzzy logic, support vector machines, and gene expression programming. The compared results shows that gene expression programming gives better results than the artificial neural network, fuzzy logic, and support vector machine with accuracy variation from 98.15 to 100%, proving the gene expression programming method can be used in transformer fault diagnosis research.

This study investigates the effects of sample size and sample prevalence on cellular automata (CA) simulation of urban growth. We take the CA models based on an artificial neural network (ANN), logistic regression (LR), and support vector machine (SVM) as examples, to simulate the urban growth of Wuhan city in China and the Wuhan Metropolitan Area under different sampling schemes. The results of the CA models based on the ANN, LR, and SVM methods are generally consistent. The sampling scheme with a small sample size and a low sample prevalence should be discarded because of the high uncertainty. Sample size determines the robustness of a CA model, whereas sample prevalence affects the performance of a CA model when there are sufficient samples. In particular, the closer the sample prevalence is to the population prevalence, the higher the simulation accuracy and the lower the shape complexity and fragmentation of the simulated urban patterns. We suggest that the optimal sampling scheme has a sample rate of 1% and a sample prevalence that is the same as the population prevalence. The selection of the optimal sampling scheme is independent of the population sizes represented by different study areas.

In this study, a new prediction model is proposed to predict the 7-day compressive strength of ultrahigh-performance concrete (UHPC) with different mix proportions using artificial neural network (ANN) and support vector machine (SVM). The predicted results are compared with the experimental results to verify the proposed model. Then, the importance of each component and the sensitivity of parameters are investigated. The research proves that the proposed model can estimate the 7-day compressive strength of UHPC based on the mix proportions.

In recent years, power quality (PQ) has become an increasingly major concern for both electric utilities and the end users. Accordingly, the electrical engineering community has to deal with the analysis, diagnosis, and solution of PQ issues using system approach rather than handling these issues as individual problems. This chapter describes the analysis of PQ using advanced signal processing tools represented in Hilbert and wavelet transforms (HT-WT) and artificial intelligence tools represented in artificial neural network and support vector machine (ANN-SVM) for detection and classification of power quality disturbances, respectively. These techniques were successfully simulated using LABVIEW software capabilities. The results of simulation indicate that the signal processing techniques are effective mechanisms to detect and classify power quality disturbances. At the end, the combination of WT as a tool of detection and features extraction with SVM as a classifier tool resulted as the best combination for PQ monitoring system.

Licensing services is one of the forms of public services that important in supporting increased investment in Indonesia and is currently carried out by the Investment and Licensing Services Department. The problems that occur in general are the length of time to process licenses and one of the contributing factors is the limited number of licensing officers. Licensing data is a time series data which have monthly observation. The Artificial Neural Network (ANN) and Support Vector Machine (SVR) is used as machine learning techniques to predict licensing pattern based on time series data. Of the data used dataset 1 and dataset 2, the sharing of training data and testing data is equal to 70% and 30% with consideration that training data must be more than testing data. The result of the study showed for Dataset 1, the ANN-Multilayer Perceptron have a better performance than Support Vector Regression (SVR) with MSE, MAE and RMSE values is 251.09, 11.45, and 15.84. Then for dataset 2, SVR-Linear has better performance than MLP with values of MSE, MAE and RMSE of 1839.93, 32.80, and 42.89. The dataset used to predict the number of permissions is dataset 2. The study also used the Simple Linear Regression (SLR) method to see the causal relationship between the number of licenses issued and licensing service officers. The result is that the relationship between the number of licenses issued and the number of service officers is less significant because there are other factors that affect the number of licenses.

Classification of grape seed species is a useful tool to obtain seeds with desired quality traits. This study aimed at rapidly and nondestructively discriminating four varieties of grape seeds using ultra violet, visible and near infrared (UV-VIS-NIR) spectroscopy with wavelength range of 210­1100 nm. A hundred twenty grape seed samples were divided for calibration (n=80) and validation (n=40). The spectra were subjected to a principal component analysis (PCA) with the leading 10 principal components (PCs) used to build calibration models. The obtained PCs were treated by linear discriminant analysis (LDA), artificial neural network (ANN) and support vector machine (SVM) to build various discrimination models. Validation results showed that the PC-LDA model developed for the full range of UV-VIS-NIR achieved better performance than those developed for partial wavelengths, i.e. UV, VIS, NIR, UV-VIS, and VIS-NIR. The PC-LDA model with 8 PCs achieved best performance with 100% discrimination accuracy. This experiment suggests that the UV-VIS-NIR spectroscopy coupled with PC-LDA calibration method is promising for the nondestructive discrimination of grape seed varieties.

The aim of this study is to realize radar emitter Identification with high-efficiency. In this article, an approach based on naive Bayesian algorithm is introduced. For recognizing radar radiations, this paper utilizes Naive Bayes classifier for radar signal sorting, and selects the pulse parameters (direction of arrival, pulse width, pulse repetition frequency and radar frequency) as features for training the classifier. The paper also compares the method based on naive Bayesian algorithm with the methods based on artificial neural network, K-means algorithm and support vector machine. The performance evaluation shows that naive Bayes classifier can achieve a high recognition accuracy, and the approach presented in this article is proved to be more efficient.

Credit scoring is an important finance activity. Both statistical techniques and Artificial Intelligence (AI) techniques have been explored for this topic. But different techniques have different advantages and disadvantages on different datasets. Recent studies draw no consistent conclusions to show that one technique is superior to the other, while they suggest combining multiple classifiers, i.e., ensemble learning, may have a better performance. In this study, we conduct an empirical evaluation of the performance of three popular ensemble methods, i.e., bagging, boosting, and stacking, based on four base learners, i.e., Logistic Regression Analysis (LRA), Decision Tree (DT), Artificial Neural Network (ANN) and Support Vector Machine (SVM). The experiment uses the credit dataset including 239 companies’ financial records from China, collected by the Industrial and Commercial Bank of China. Results reveal that ensemble learning can substantially improve individual base learners. Stacking, in our experiments, gets the best performance in terms of all six performance indicators, i.e., type I error, type II error, average accuracy, precision, recall, and F-value.

The purpose of this retrospective study is to measure machine learning models' ability to predict glaucoma drainage device failure based on demographic information and preoperative measurements. The medical records of 165 patients were used. Potential predictors included the patients' race, age, sex, preoperative intraocular pressure (IOP), preoperative visual acuity, number of IOP-lowering medications, and number and type of previous ophthalmic surgeries. Failure was defined as final IOP greater than 18 mm Hg, reduction in intraocular pressure less than 20% from baseline, or need for reoperation unrelated to normal implant maintenance. Five classifiers were compared: logistic regression, artificial neural network, random forest, decision tree, and support vector machine. Recursive feature elimination was used to shrink the number of predictors and grid search was used to choose hyperparameters. To prevent leakage, nested cross-validation was used throughout. With a small amount of data, the best classfier was logistic regression, but with more data, the best classifier was the random forest.

Feature extraction and classification of electroencephalogram (EEG) signal for normal and epileptic patients is one of the most challenging research areas in the field of biomedical signal processing. Epileptic seizures are manifestations of epilepsy. Several techniques have been used for feature extraction and classification of EEG in last decades. In this article, non-negative matrix factorization (NMF) has been used for feature extraction of EEG signals and the classifiers used are Artificial Neural Network (ANN) and support vector machine (SVM). For NMF, fast Fourier transform (FFT) is used for feature extraction of the EEG signal. Performances of classifiers are measured on the parameters: accuracy, sensitivity and specificity. It has been observed that NMF gives satisfactory results for feature extraction and classification of EEG signal.

This paper presents a novel technique based on time-frequency analysis to detect the islanding conditions in distribution network with the presence of multiple distributed generations (DGs).Various islanding and non-islanding fault conditions such as capacitor switching, load rejection and line to line fault etc., are analyzed through negative sequence decomposition technique. Feature extraction has been carried out by two time–frequency analysis techniques based on wavelet transform (WT) and S-Transform (ST). For the detection of various disturbances the energy and standard deviation (SD) features of signals are estimated by wavelet transform coefficient and S-transform matrix. Furthermore, based on the estimated features the artificial neural network (ANN) and support vector machine (SVM) are used as a classifier to classify the islanding and non-islanding events. For showing the effectiveness of the proposed technique to detect islanding conditions under a wide range of operating environment, some simulated results are presented.

Computers and artificial intelligence have penetrated in the food industry since last decade, for intellectual automatic processing and packaging in general, and in assisting for quality inspection of the food itself in particular. The food quality assessment task becomes more challenging when it is about harmless internal examination of the ingredient, and even more when its size is also minute. In this article, a method for automatic detection, extraction and classification of raw food item is presented using x-ray image data of pine nuts. Image processing techniques are employed in developing an efficient method for automatic detection and then extraction of individual ingredient, from the source x-ray image which comprises bunch of nuts in a single frame. For data representation, statistical texture analysis is carried out and attributes are calculated from each of the sample image on the global level as features. In addition co-occurrence matrices are computed from images with four different offsets, and hence more features are extracted by using them. To find fewer meaningful characteristics, all the calculated features are organized in several combinations and then tested. Seventy percent of image data is used for training and 15% each for cross-validation and test purposes. Binary classification is performed using two state-of-the-art non-linear classifiers: Artificial Neural Network (ANN) and Support Vector Machines (SVM). Performance is evaluated in terms of classification accuracy, specificity and sensitivity. ANN classifier showed 87.6% accuracy with correct recognition rate of healthy nuts and unhealthy nuts as 94% and 62% respectively. SVM classifier produced the similar accuracy achieving 86.3% specificity and 89.2% sensitivity rate. The results obtained are unique itself in terms of ingredient and promising relatively. It is also found that feature set size can be reduced up to 57% by compromising 3.5% accuracy, in combination with any of the tested classifiers.