Bankruptcy has long been an important topic in finance and accounting research. Recent headline bankruptcies have included Enron, Fannie Mae, Freddie Mac, Washington Mutual, Merrill Lynch, and Lehman Brothers. These bankruptcies and their financial fallout have become a serious public concern due to huge influence these companies play in the real economy. Many researchers began investigating bankruptcy predictions back in the early 1970s. However, until recently, most research used prediction models based on traditional statistics. In recent years, however, newly-developed data mining techniques have been applied to various fields, including performance prediction systems. This research applies particle swarm optimization (PSO) to obtain suitable parameter settings for a support vector machine (SVM) model and to select a subset of beneficial features without reducing the classification accuracy rate. Experiments were conducted on an initial sample of 80 electronic companies listed on the Taiwan Stock Exchange Corporation (TSEC).
This paper makes four critical contributions: (1) The results indicate the business cycle factor mainly affects financial prediction performance and has a greater influence than financial ratios. (2) The closer we get to the actual occurrence of financial distress, the higher the accuracy obtained both with and without feature selection under the business cycle approach. For example, PSO-SVM without feature selection provides 89.37% average correct cross-validation for two quarters prior to the occurrence of financial distress. (3) Our empirical results show that PSO integrated with SVM provides better classification accuracy than the Grid search, and genetic algorithm (GA) with SVM approaches for companies as normal or under threat. (4) The PSO-SVM model also provides better prediction accuracy than do the Grid-SVM, GA-SVM, SVM, SOM, and SVR-SOM approaches for seven well-known UCI datasets. Therefore, this paper proposes that the PSO-SVM approach could be a more suitable method for predicting potential financial distress.
An effective and novel roller bearing fault diagnosis technique based on empirical mode decomposition (EMD) energy entropy and support vector machine (SVM) is put forward in this article. The vibration signal of roller bearing is decomposed by EMD and the first 5 intrinsic mode function (IMF) components are obtained. SVM served as a fault diagnosis classifier and the extracted energy features of the first 5 IMFs are taken as network input vectors, and then the fault bearing and the normal bearing can be distinguished. An technique for fault of roller bearing by SVM is evaluated against a series of fault diagnosis methods that are widely used in machinery, with particular regard to the effect of training set size on fault diagnosis accuracy. We trained the SVM using RBF kernel function. We compare our experimental results with the existing results given by SMO and SVM-light algorithms. It can be seen that the fault diagnosis method based on SVM-light is superior to that based on SMO in diagnosis accuracy of roller bearing. In addition to the SVM, the same datasets were classified using RBF NN and Hopfield NN. The experimental results show that the technique of support vector machine based on EMD energy entropy has higher fault diagnosis ability.
In recent years the interest of the investors in efficient methods for the forecasting price trend of a share in financial markets has grown steadily. The aim is to accurately forecast the future behavior of the market in order to identificate the so-called "correct timing".
In this paper we analyze three different approaches for forecasting financial data: Autoregression, artificial neural networks and support vector machines and we will determine potentials and limits of these methods. Application to the Italian financial market is also presented.
This paper compares Fuzzy Inference System (FIS), Support Vector Machine (SVM) and MultiLayer Feed-forward neural network (MLF) in modeling a driver's decision when making a discretionary lane changing move on a freeway. The FIS model has been developed and published in an earlier work by the authors, whereas the SVM and MLF models are newly developed in this research. The FIS, SVM and MLF models use the same four inputs: the gap between the subject vehicle and the leading vehicle in the original lane, the gap between the subject vehicle and the leading vehicle in the destination lane, the gap between the subject vehicle and the trailing vehicle in the destination lane, and the distance between the preceding and trailing vehicles in the destination lane. The models give a binary decision of "no, stay in the same lane" or "yes, move to the destination lane now". These models were trained and then tested with the Next Generation SIMulation (NGSIM) vehicle trajectory data. The results have shown that the FIS has the highest accuracies in making correct lane changing decisions. It recommends "yes, move to the destination lane now" with 82.2% accuracy, and "no, stay in the same lane" with 99.5% accuracy. The SVM model also outperformed the traditional gap acceptance model which was used as the benchmark. However, the MLF model was not as accurate as the gap acceptance model.
This paper presents an algorithm for the design of a computer aided diagnosis system to detect, quantify and classify the lesions of non-proliferative diabetic retinopathy as well as dry age related macular degeneration from the fundus retina images. Symptoms of non-proliferative diabetic retinopathy in images consist of bright lesions like hard exudates, cotton wool spots and dark lesions like microaneurysms, hemorrhages. Dry age related macular degeneration is manifested as a bright lesion called drusen. The proposed system consists of two parts: image processing, where preprocessed gray scale images are segmented to extract candidate lesions using a combination of Gaussian filtering and multilevel thresholding followed by classification of the different lesions in non-proliferative diabetic retinopathy and age related macular degeneration using perceptron, support vector machine and naive Bayes classifier. From the comparative performance analysis of the classification techniques, it is observed that comparable results are obtained from single layer perceptron and support vector machine and they both outperform naive Bayes classifier. The classification accuracy of support vector machine classifier for dark lesion class is 97.13% and the classification accuracy of single layer perceptron for bright lesion class is 95.13% with optimal feature set.
Alzheimer's Disease (AD) is the most frequent form of degenerative dementia and its early diagnosis is essential for effective treatment. Functional imaging modalities including Single Photon Emission Computed Tomography (SPECT) are often used with such an aim. However, conventional evaluation of SPECT images relies on manual reorientation and visual evaluation of tomographic slices which is time consuming, subjective and therefore prone to error. Our aim is to show an automatic Computer-Aided Diagnosis (CAD) system for improving the early detection of the AD. For this purpose, affine invariant descriptors of 3D SPECT image can be useful. The method consists of four steps: evaluation of invariant descriptors obtained using spherical harmonic analysis, statistical testing of their significance, application of regularized binary index models, and model verification via leave-one-out cross-validation scheme. The second approach is based on Support Vector Machine (SVM) classifier and visualization with use of self-organizing maps. Our approaches were tested on SPECT data from 11 adult patients with definite Alzheimer's disease and 10 adult patients with Amyotrophic Lateral Sclerosis (ALS) who were used as controls. A significant difference between SPECT spherical cuts of AD group and ALS group was both visually and numerically evaluated.
Forecasting arrival times of a vehicle at many downstream stops is very important in many cases. For multi-stop arrival time prediction, direct approaches and iterative approaches possess respective merits. Therefore, a hybrid method that has both direct and iterative modeling abilities is presented to forecast arrival times at multiple stops. The hybrid method consists of an iterative support vector machine (SVM)-based prediction model and a direct SVM-based prediction model. In hybrid model, output from the iterative model is a rough prediction and it also needs to be adjusted, based on output from the direct model. The proposed model is assessed with the data of transit route number 3 in Guiyang city, China. Results show that the hybrid model seems to be a powerful tool for multi-stop arrival time prediction.
Train-induced vibration prediction in multi-story buildings can effectively provide the effect of vibrations on buildings. With the results of prediction, the corresponding measures can be used to reduce the influence of the vibrations. To accurately predict the vibrations induced by train in multi-story buildings, support vector machine (SVM) is used in this paper. Since the parameters in SVM are very vital for the prediction accuracy, shuffled frog-leaping algorithm (SFLA) is used to optimize the parameters for SVM. The proposed model is evaluated with the data from field experiments. The results show SFLA can effectively provide better parameter values for SVM and the SVM models outperform a better performance than artificial neural network (ANN) for train-induced vibration prediction