Machine vision for the automatic classification of images acquired from Non-destructive tests

This project is based on Artificial Intelligence (A.I) and Digital Image processing (I.P) for automatic condition monitoring of sleepers in the railway track. Rail inspection is a very important task in railway maintenance for traffic safety issues and in preventing dangerous situations. Monitoring railway track infrastructure is an important aspect in which the periodical inspection of rail rolling plane is required.Up to the present days the inspection of the railroad is operated manually by trained personnel. A human operator walks along the railway track searching for sleeper anomalies. This monitoring way is not more acceptable for its slowness and subjectivity. Hence, it is desired to automate such intuitive human skills for the development of more robust and reliable testing methods. Images of wooden sleepers have been used as data for my project. The aim of this project is to present a vision based technique for inspecting railway sleepers (wooden planks under the railway track) by automatic interpretation of Non Destructive Test (NDT) data using A.I. techniques in determining the results of inspection.

Simultaneous prediction of symptom severity and cause in data from a test battery for Parkinson patients, using machine learning methods

The main purpose of this thesis project is to prediction of symptom severity and cause in data from test battery of the Parkinson’s disease patient, which is based on data mining. The collection of the data is from test battery on a hand in computer. We use the Chi-Square method and check which variables are important and which are not important. Then we apply different data mining techniques on our normalize data and check which technique or method gives good results.The implementation of this thesis is in WEKA. We normalize our data and then apply different methods on this data. The methods which we used are Naïve Bayes, CART and KNN. We draw the Bland Altman and Spearman’s Correlation for checking the final results and prediction of data. The Bland Altman tells how the percentage of our confident level in this data is correct and Spearman’s Correlation tells us our relationship is strong. On the basis of results and analysis we see all three methods give nearly same results. But if we see our CART (J48 Decision Tree) it gives good result of under predicted and over predicted values that’s lies between -2 to +2. The correlation between the Actual and Predicted values is 0,794in CART. Cause gives the better percentage classification result then disability because it can use two classes.

Classification of Parkinson’s Disease using MultiPass Lvq,Logistic Model Tree,K-Star for Audio Data set : Classification of Parkinson Disease using Audio Dataset

Parkinson's disease (PD) is a degenerative illness whose cardinal symptoms include rigidity, tremor, and slowness of movement. In addition to its widely recognized effects PD can have a profound effect on speech and voice.The speech symptoms most commonly demonstrated by patients with PD are reduced vocal loudness, monopitch, disruptions of voice quality, and abnormally fast rate of speech. This cluster of speech symptoms is often termed Hypokinetic Dysarthria.The disease can be difficult to diagnose accurately, especially in its early stages, due to this reason, automatic techniques based on Artificial Intelligence should increase the diagnosing accuracy and to help the doctors make better decisions. The aim of the thesis work is to predict the PD based on the audio files collected from various patients.Audio files are preprocessed in order to attain the features.The preprocessed data contains 23 attributes and 195 instances. On an average there are six voice recordings per person, By using data compression technique such as Discrete Cosine Transform (DCT) number of instances can be minimized, after data compression, attribute selection is done using several WEKA build in methods such as ChiSquared, GainRatio, Infogain after identifying the important attributes, we evaluate attributes one by one by using stepwise regression.Based on the selected attributes we process in WEKA by using cost sensitive classifier with various algorithms like MultiPass LVQ, Logistic Model Tree(LMT), K-Star.The classified results shows on an average 80%.By using this features 95% approximate classification of PD is acheived.This shows that using the audio dataset, PD could be predicted with a higher level of accuracy.

Speech Assessment for the Classification of Hypokinetic Dysthria in Parkinson Disease

The aim of this thesis is to investigate computerized voice assessment methods to classify between the normal and Dysarthric speech signals. In this proposed system, computerized assessment methods equipped with signal processing and artificial intelligence techniques have been introduced. The sentences used for the measurement of inter-stress intervals (ISI) were read by each subject. These sentences were computed for comparisons between normal and impaired voice. Band pass filter has been used for the preprocessing of speech samples. Speech segmentation is performed using signal energy and spectral centroid to separate voiced and unvoiced areas in speech signal. Acoustic features are extracted from the LPC model and speech segments from each audio signal to find the anomalies. The speech features which have been assessed for classification are Energy Entropy, Zero crossing rate (ZCR), Spectral-Centroid, Mean Fundamental-Frequency (Meanf0), Jitter (RAP), Jitter (PPQ), and Shimmer (APQ). Naïve Bayes (NB) has been used for speech classification. For speech test-1 and test-2, 72% and 80% accuracies of classification between healthy and impaired speech samples have been achieved respectively using the NB. For speech test-3, 64% correct classification is achieved using the NB. The results direct the possibility of speech impairment classification in PD patients based on the clinical rating scale.

Predictive models for chronic renal disease using decision trees, naïve bayes and case-based methods

Data mining can be used in healthcare industry to “mine” clinical data to discover hidden information for intelligent and affective decision making. Discovery of hidden patterns and relationships often goes intact, yet advanced data mining techniques can be helpful as remedy to this scenario. This thesis mainly deals with Intelligent Prediction of Chronic Renal Disease (IPCRD). Data covers blood, urine test, and external symptoms applied to predict chronic renal disease. Data from the database is initially transformed to Weka (3.6) and Chi-Square method is used for features section. After normalizing data, three classifiers were applied and efficiency of output is evaluated. Mainly, three classifiers are analyzed: Decision Tree, Naïve Bayes, K-Nearest Neighbour algorithm. Results show that each technique has its unique strength in realizing the objectives of the defined mining goals. Efficiency of Decision Tree and KNN was almost same but Naïve Bayes proved a comparative edge over others. Further sensitivity and specificity tests are used as statistical measures to examine the performance of a binary classification. Sensitivity (also called recall rate in some fields) measures the proportion of actual positives which are correctly identified while Specificity measures the proportion of negatives which are correctly identified. CRISP-DM methodology is applied to build the mining models. It consists of six major phases: business understanding, data understanding, data preparation, modeling, evaluation, and deployment.

Decision Tree Classification Model In Water Supply Network

With the service life of water supply network (WSN) growth, the growing phenomenon of aging pipe network has become exceedingly serious. As urban water supply network is hidden underground asset, it is difficult for monitoring staff to make a direct classification towards the faults of pipe network by means of the modern detecting technology. In this paper, based on the basic property data (e.g. diameter, material, pressure, distance to pump, distance to tank, load, etc.) of water supply network, decision tree algorithm (C4.5) has been carried out to classify the specific situation of water supply pipeline. Part of the historical data was used to establish a decision tree classification model, and the remaining historical data was used to validate this established model. Adopting statistical methods were used to access the decision tree model including basic statistical method, Receiver Operating Characteristic (ROC) and Recall-Precision Curves (RPC). These methods has been successfully used to assess the accuracy of this established classification model of water pipe network. The purpose of classification model was to classify the specific condition of water pipe network. It is important to maintain the pipeline according to the classification results including asset unserviceable (AU), near perfect condition (NPC) and serious deterioration (SD). Finally, this research focused on pipe classification which plays a significant role in maintaining water supply networks in the future.

Efficient supervised optimum-path forest classification for large datasets

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Submucous fibroids classification - STEP-W classification

Objective: To develop a new submucous fibroids classification for evaluating the viability and the degree of difficulty and complexity of a hysteroscopic myomectomy.Methods: We have included more four parameters in addition to penetration the fibroid into the myometrium. The extra-parameters were: size of the fibroid, it topography, it extension of the base in relation the wall was set and the wall it was set. The fibroids were classified according to the Classification of the European Society for Gynaecological Endoscopy (ESGE) and to the new classification (STEP-W) in patients who were submitted to hysteroscopic resection of submucous fibroids. The possibility of total resection of the fibroid, the operating time, the fluid deficit and the frequency of any complications were considered. The Fisher test, the Student t test and the analysis of variance test were used in the statistical analyses. It was considered statistically significant when the p-value was less than 0.05 in the two-tailed test.Results: In group which the hysteroscopic surgery was considered complete there was no significant difference between the three ESGE levels (0, 1 and 2). Using the STEP-W, the difference between the numbers of complete surgeries was significant (p < 0.001) for the two levels (groups I and II). The difference between the operating times was significant for the two classifications. In relation to the fluid deficit, only the STEP-W showed significant differences between the levels (p=0.02).Conclusions: It seems to us that the new classification (STEP-W) gives more clues to the difficulties of a hysteroscopic myornectomy than the standard classification (ESGE).

Traumatic subdural hygromas: Proposed pathogenesis based classification

Background: Traumatic subdural hygroma (TSHy) is an accumulation of cerebrospinal fluid (CSF) in the subdural space after head injury. It appears to be relatively common, but its onset time and natural history are not well defined. Considered a benign epiphenomenon of trauma, the pathogenesis of TSHy is still unclear and many questions remain unanswered. This study adds to the information on TSHy, and proposes a classification based on pathogenesis.Methods: Thirty-four consecutive adult patients with TSHy were analyzed for clinical evolution and serial CT scan, during a period of several months. TSHy diagnosis was based on published CT scan criteria of hypodense subdural collection after trauma, without enhancement and neomembrane, with a minimum distance of 3 mm between the skull and brain. Ventricle size was analyzed by calculating the bicaudate index (BCI). For comparison, the BCI was measured from CT scan at three moments: admission, at time of TSHy diagnosis, and from last CT scan.Results: There were 34 patients, aged between 16 and 85 years (mean 40), half of them were below 40 years. Road traffic crashes were the main cause of head injury. The mean time for hygroma diagnosis was 9 days. Twenty-one patients (61.8%) underwent conservative treatment for TSHy and 13 (38.2%), surgical treatment. TSHy are early lesions and can be detected in the first 24 hours after trauma, usually as small subdural effusion (SSEff). Based on clinical and CT scan findings, we divided the 34 patients into 3 groups, (Ia and Ib) without evident mass effect and (II) with evident mass effect. Group Ia includes patients without ventricle dilation; Ib, patients with associated ventricle dilations.Conclusions: SSEff detected in the first 24 hours posttrauma in our series evolved into TSHy suggesting that this is an early lesion; all THSy were divided in three groups according to the pathophysiologic mechanism. These three groups probably represent a continuum of CSF absorption impairment. Group la represents what most authors consider a simple hygroma, with no impairment on CSF absorption. Group Ib represent the external hydrocephalus form with various degrees of CSF imbalance, and group II were the cases presenting marked mass effect.

Comparison of three systems of classification in predicting the outcome of diabetic foot ulcers in a Brazilian population

Objective: The aim was to compare there ulcer classification systems as predictors of the outcome of diabetic foot ulcers; the Wagner, the University of Texas (UT) and the size (area, depth), sepsis, arteriopathy, denervation system (S(AD)SAD) systems in specialist clinic in Brazil.Methods: Ulcer area, depth, appearance, infection and associated ischaemia and neuropathy were recorded in a consecutive series of 94 subjects. A novel score, the S(AD)SAD score, was derived from the sum of individual items of the S(AD)SAD system, and was evaluated. Follow-up was for at least 6 months. The primary outcome measure was the incidence of healing.Results: Mean age was 57.6 years; 57 (60.6%) were made. Forty-eight ulcers (51.1%) healed without surgery; 11 (12.2%) subjects underwent minor amputation. Significant differences in terms of healing were observed for depth (P = 0.002), infection (P = 0.006) and denervation (P = 0.002) using the S(AD)SAD system, for UT grade (P = 0.002) and stage (P = 0.032) and for Wagner grades (P = 0.002). Ulcers with an S(AD)SAD score of <= 9 (total possible 15) were 7.6 times more likely to heal than scores >= 10 (P < 0.001).Conclusions: All three systems predicted ulcer outcome. The S(AD)SAD score of ulcer severity could represent a useful addition to routine clinical practice. The association between outcome and ulcer depth confirms earlier reports. The association with infection was stronger than that reported from the centres in Europe or North America. The very strong association with neuropathy has only previously been observed in Tanzania. Studies designed to compare the outcome in different countries should adopt systems of classification, which are valid for the populations studied.

Shape-based features for cat ganglion retinal cells classification

This article presents a quantitative and objective approach to cat ganglion cell characterization and classification. The combination of several biologically relevant features such as diameter, eccentricity, fractal dimension, influence histogram, influence area, convex hull area, and convex hull diameter are derived from geometrical transforms and then processed by three different clustering methods (Ward's hierarchical scheme, K-means and genetic algorithm), whose results are then combined by a voting strategy. These experiments indicate the superiority of some features and also suggest some possible biological implications.

Evaluation of motivation methods used to obtain appropriate oral hygiene levels in schoolchildren.

The aim of the present study is to assess the behaviour of different motivation methods on levels of oral hygiene among schoolchildren aged from 7 to 9 years in Araraquara, SP, Brazil. The methods tested were: indirect instruction using 'The Smiling Robot' (group I), indirect instruction through class presentation (group II) and direct instruction with macromodels (group III). A control group was also constituted, which received no kind of motivation (group IV). The O'Leary Plaque Index was used as the evaluation method, applied before the instruction and 30 days after application of the different methods. It was noted that the plaque index had not decreased in group IV only. In conclusion, all the motivation methods promoted significant decrease of plaque index and among these methods, the 'The Smiling Robot' was the one that provided the best results.

Fault identification in distribution lines using intelligent systems and statistical methods

The main objective involved with this paper consists of presenting the results obtained from the application of artificial neural networks and statistical tools in the automatic identification and classification process of faults in electric power distribution systems. The developed techniques to treat the proposed problem have used, in an integrated way, several approaches that can contribute to the successful detection process of faults, aiming that it is carried out in a reliable and safe way. The compilations of the results obtained from practical experiments accomplished in a pilot distribution feeder have demonstrated that the developed techniques provide accurate results, identifying and classifying efficiently the several occurrences of faults observed in the feeder. © 2006 IEEE.

Malware distributed collection and pre-classification system using honeypot technology

Malware has become a major threat in the last years due to the ease of spread through the Internet. Malware detection has become difficult with the use of compression, polymorphic methods and techniques to detect and disable security software. Those and other obfuscation techniques pose a problem for detection and classification schemes that analyze malware behavior. In this paper we propose a distributed architecture to improve malware collection using different honeypot technologies to increase the variety of malware collected. We also present a daemon tool developed to grab malware distributed through spam and a pre-classification technique that uses antivirus technology to separate malware in generic classes. © 2009 SPIE.

Classification of petroleum well drilling operations with a hybrid particle swarm/ant colony algorithm

This paper describes an investigation of the hybrid PSO/ACO algorithm to classify automatically the well drilling operation stages. The method feasibility is demonstrated by its application to real mud-logging dataset. The results are compared with bio-inspired methods, and rule induction and decision tree algorithms for data mining. © 2009 Springer Berlin Heidelberg.