Spectral clustering independent component analysis for tissue classification from brain MRI

A spectral angle based feature extraction method, Spectral Clustering Independent Component Analysis (SC-ICA), is proposed in this work to improve the brain tissue classification from Magnetic Resonance Images (MRI). SC-ICA provides equal priority to global and local features; thereby it tries to resolve the inefficiency of conventional approaches in abnormal tissue extraction. First, input multispectral MRI is divided into different clusters by a spectral distance based clustering. Then, Independent Component Analysis (ICA) is applied on the clustered data, in conjunction with Support Vector Machines (SVM) for brain tissue analysis. Normal and abnormal datasets, consisting of real and synthetic T1-weighted, T2-weighted and proton density/fluid-attenuated inversion recovery images, were used to evaluate the performance of the new method. Comparative analysis with ICA based SVM and other conventional classifiers established the stability and efficiency of SC-ICA based classification, especially in reproduction of small abnormalities. Clinical abnormal case analysis demonstrated it through the highest Tanimoto Index/accuracy values, 0.75/98.8%, observed against ICA based SVM results, 0.17/96.1%, for reproduced lesions. Experimental results recommend the proposed method as a promising approach in clinical and pathological studies of brain diseases

Wavelet based Independent Component Analysis for Multispectral Brain Tissue Classification

Multispectral analysis is a promising approach in tissue classification and abnormality detection from Magnetic Resonance (MR) images. But instability in accuracy and reproducibility of the classification results from conventional techniques keeps it far from clinical applications. Recent studies proposed Independent Component Analysis (ICA) as an effective method for source signals separation from multispectral MR data. However, it often fails to extract the local features like small abnormalities, especially from dependent real data. A multisignal wavelet analysis prior to ICA is proposed in this work to resolve these issues. Best de-correlated detail coefficients are combined with input images to give better classification results. Performance improvement of the proposed method over conventional ICA is effectively demonstrated by segmentation and classification using k-means clustering. Experimental results from synthetic and real data strongly confirm the positive effect of the new method with an improved Tanimoto index/Sensitivity values, 0.884/93.605, for reproduced small white matter lesions

“Improved Feature Extraction and Classification Techniques for Multispectral Brain Magnetic Resonance Images”

Magnetic Resonance Imaging (MRI) is a multi sequence medical imaging technique in which stacks of images are acquired with different tissue contrasts. Simultaneous observation and quantitative analysis of normal brain tissues and small abnormalities from these large numbers of different sequences is a great challenge in clinical applications. Multispectral MRI analysis can simplify the job considerably by combining unlimited number of available co-registered sequences in a single suite. However, poor performance of the multispectral system with conventional image classification and segmentation methods makes it inappropriate for clinical analysis. Recent works in multispectral brain MRI analysis attempted to resolve this issue by improved feature extraction approaches, such as transform based methods, fuzzy approaches, algebraic techniques and so forth. Transform based feature extraction methods like Independent Component Analysis (ICA) and its extensions have been effectively used in recent studies to improve the performance of multispectral brain MRI analysis. However, these global transforms were found to be inefficient and inconsistent in identifying less frequently occurred features like small lesions, from large amount of MR data. The present thesis focuses on the improvement in ICA based feature extraction techniques to enhance the performance of multispectral brain MRI analysis. Methods using spectral clustering and wavelet transforms are proposed to resolve the inefficiency of ICA in identifying small abnormalities, and problems due to ICA over-completeness. Effectiveness of the new methods in brain tissue classification and segmentation is confirmed by a detailed quantitative and qualitative analysis with synthetic and clinical, normal and abnormal, data. In comparison to conventional classification techniques, proposed algorithms provide better performance in classification of normal brain tissues and significant small abnormalities.

Brain Tissue Classification from Multispectral MRI by Wavelet based Principal Component Analysis

In this paper, we propose a multispectral analysis system using wavelet based Principal Component Analysis (PCA), to improve the brain tissue classification from MRI images. Global transforms like PCA often neglects significant small abnormality details, while dealing with a massive amount of multispectral data. In order to resolve this issue, input dataset is expanded by detail coefficients from multisignal wavelet analysis. Then, PCA is applied on the new dataset to perform feature analysis. Finally, an unsupervised classification with Fuzzy C-Means clustering algorithm is used to measure the improvement in reproducibility and accuracy of the results. A detailed comparative analysis of classified tissues with those from conventional PCA is also carried out. Proposed method yielded good improvement in classification of small abnormalities with high sensitivity/accuracy values, 98.9/98.3, for clinical analysis. Experimental results from synthetic and clinical data recommend the new method as a promising approach in brain tissue analysis.

STUDIES ON THE STRESS FLUCTUATIONS IN SHEARED STOKESIAN SUSPENSIONS USING CHAOS THEORY AND NONLINEAR DYNAMICS

The thesis report results obtained from a detailed analysis of the fluctuations of the rheological parameters viz. shear and normal stresses, simulated by means of the Stokesian Dynamics method, of a macroscopically homogeneous sheared suspension of neutrally buoyant non-Brownian suspension of identical spheres in the Couette gap between two parallel walls in the limit of vanishingly small Reynolds numbers using the tools of non-linear dynamics and chaos theory for a range of particle concentration and Couette gaps. The thesis used the tools of nonlinear dynamics and chaos theory viz. average mutual information, space-time separation plots, visual recurrence analysis, principal component analysis, false nearest-neighbor technique, correlation integrals, computation of Lyapunov exponents for a range of area fraction of particles and for different Couette gaps. The thesis observed that one stress component can be predicted using another stress component at the same area fraction. This implies a type of synchronization of one stress component with another stress component. This finding suggests us to further analysis of the synchronization of stress components with another stress component at the same or different area fraction of particles. The different model equations of stress components for different area fraction of particles hints at the possible existence a general formula for stress fluctuations with area fraction of particle as a parameter

Studies on the Quality of Rainwater at Various Land Use Locations and Variations by Interaction with Domestic Rainwater Harvesting Systems

The present study focused on the quality of rainwater at various land use locations and its variations on interaction with various domestic rainwater harvesting systems.Sampling sites were selected based upon the land use pattern of the locations and were classified as rural, urban, industrial and sub urban. Rainwater samples were collected from the south west monsoon of May 2007 to north east monsoon of October 2008, from four sampling sites namely Kothamangalam, Emakulam, Eloor and Kalamassery, in Ernakulam district of the State of Kerala, which characterized typical rural, urban, industrial and suburban locations respectively. Rain water samples at various stages of harvesting were also collected. The samples were analyzed according to standard procedures and their physico-chemical and microbiological parameters were determined. The variations of the chemical composition of the rainwater collected were studied using statistical methods. It was observed that 17.5%, 30%, 45.8% and 12.1% of rainwater samples collected at rural, urban, industrial and suburban locations respectively had pH less than 5.6, which is considered as the pH of cloud water at equilibrium with atmospheric CO,.Nearly 46% of the rainwater samples were in acidic range in the industrial location while it was only 17% in the rural location. Multivariate statistical analysls was done using Principal Component Analysis, and the sources that inf1uence the composition of rainwater at each locations were identified .which clearly indicated that the quality of rain water is site specific and represents the atmospheric characteristics of the free fall The quality of harvested rainwater showed significant variations at different stages of harvesting due to deposition of dust from the roof catchment surface, leaching of cement constituents etc. Except the micro biological quality, the harvested rainwater satisfied the Indian Standard guide lines for drinking water. Studies conducted on the leaching of cement constituents in water concluded that tanks made with ordinary portland cement and portland pozzolana cement could be safely used for storage of rain water.

A Prototype for a Multimodal Biometric Security system based on Face and Audio Signatures

Any automatically measurable, robust and distinctive physical characteristic or personal trait that can be used to identify an individual or verify the claimed identity of an individual, referred to as biometrics, has gained significant interest in the wake of heightened concerns about security and rapid advancements in networking, communication and mobility. Multimodal biometrics is expected to be ultra-secure and reliable, due to the presence of multiple and independent—verification clues. In this study, a multimodal biometric system utilising audio and facial signatures has been implemented and error analysis has been carried out. A total of one thousand face images and 250 sound tracks of 50 users are used for training the proposed system. To account for the attempts of the unregistered signatures data of 25 new users are tested. The short term spectral features were extracted from the sound data and Vector Quantization was done using K-means algorithm. Face images are identified based on Eigen face approach using Principal Component Analysis. The success rate of multimodal system using speech and face is higher when compared to individual unimodal recognition systems

Biogeochemistry of the shelf sediments of south eastern Arabian sea: Effect on benthic bacterial heterotrophs

The composition and variability of heterotrophic bacteria along the shelf sediments of south west coast of India and its relationship with the sediment biogeochemistry was investigated. The bacterial abundance ranged from 1.12 x 103 – 1.88 x 106 CFU g-1 dry wt. of sediment. The population showed significant positive correlation with silt (r = 0.529, p< 0.05), organic carbon (OC) (r = 0.679, p< 0.05), total nitrogen (TN) (r = 0.638, p< 0.05), total protein (TPRT) (r = 0.615, p< 0.05) and total carbohydrate (TCHO) (r = 0.675, p< 0.05) and significant negative correlation with sand (r = -0.488, p< 0.05). Community was mainly composed of Bacillus, Alteromonas, Vibrio, Coryneforms, Micrococcus, Planococcus, Staphylococcus, Moraxella, Alcaligenes, Enterobacteriaceae, Pseudomonas, Acinetobacter, Flavobacterium and Aeromonas. BIOENV analysis explained the best possible environmental parameters i.e., carbohydrate, total nitrogen, temperature, pH and sand at 50m depth and organic matter, BPC, protein, lipid and temperature at 200m depth controlling the distribution pattern of heterotrophic bacterial population in shelf sediments. The Principal Component Analysis (PCA) of the environmental variables showed that the first and second principal component accounted for 65% and 30.6% of the data variance respectively. Canonical Correspondence Analysis (CCA) revealed a strong correspondence between bacterial distribution and environmental variables in the study area. Moreover, non-metric MDS (Multidimensional Scaling) analysis demarcated the northern and southern latitudes of the study area based on the bioavailable organic matter

A System for Offline Recognition of Handwritten Characters in Malayalam Script

In this paper, we propose a handwritten character recognition system for Malayalam language. The feature extraction phase consists of gradient and curvature calculation and dimensionality reduction using Principal Component Analysis. Directional information from the arc tangent of gradient is used as gradient feature. Strength of gradient in curvature direction is used as the curvature feature. The proposed system uses a combination of gradient and curvature feature in reduced dimension as the feature vector. For classification, discriminative power of Support Vector Machine (SVM) is evaluated. The results reveal that SVM with Radial Basis Function (RBF) kernel yield the best performance with 96.28% and 97.96% of accuracy in two different datasets. This is the highest accuracy ever reported on these datasets

Performance Improvement of Fuzzy and Neuro Fuzzy Systems: Prediction of Learning Disabilities in School-age Children

Learning Disability (LD) is a classification including several disorders in which a child has difficulty in learning in a typical manner, usually caused by an unknown factor or factors. LD affects about 15% of children enrolled in schools. The prediction of learning disability is a complicated task since the identification of LD from diverse features or signs is a complicated problem. There is no cure for learning disabilities and they are life-long. The problems of children with specific learning disabilities have been a cause of concern to parents and teachers for some time. The aim of this paper is to develop a new algorithm for imputing missing values and to determine the significance of the missing value imputation method and dimensionality reduction method in the performance of fuzzy and neuro fuzzy classifiers with specific emphasis on prediction of learning disabilities in school age children. In the basic assessment method for prediction of LD, checklists are generally used and the data cases thus collected fully depends on the mood of children and may have also contain redundant as well as missing values. Therefore, in this study, we are proposing a new algorithm, viz. the correlation based new algorithm for imputing the missing values and Principal Component Analysis (PCA) for reducing the irrelevant attributes. After the study, it is found that, the preprocessing methods applied by us improves the quality of data and thereby increases the accuracy of the classifiers. The system is implemented in Math works Software Mat Lab 7.10. The results obtained from this study have illustrated that the developed missing value imputation method is very good contribution in prediction system and is capable of improving the performance of a classifier.

Learning disability prediction tool using ANN and ANFIS

Learning Disability (LD) is a neurological condition that affects a child’s brain and impairs his ability to carry out one or many specific tasks. LD affects about 15 % of children enrolled in schools. The prediction of LD is a vital and intricate job. The aim of this paper is to design an effective and powerful tool, using the two intelligent methods viz., Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System, for measuring the percentage of LD that affected in school-age children. In this study, we are proposing some soft computing methods in data preprocessing for improving the accuracy of the tool as well as the classifier. The data preprocessing is performed through Principal Component Analysis for attribute reduction and closest fit algorithm is used for imputing missing values. The main idea in developing the LD prediction tool is not only to predict the LD present in children but also to measure its percentage along with its class like low or minor or major. The system is implemented in Mathworks Software MatLab 7.10. The results obtained from this study have illustrated that the designed prediction system or tool is capable of measuring the LD effectively

Towards the development of a new wavelet for ECG classification

In this paper an attempt has been made to determine the number of Premature Ventricular Contraction (PVC) cycles accurately from a given Electrocardiogram (ECG) using a wavelet constructed from multiple Gaussian functions. It is difficult to assess the ECGs of patients who are continuously monitored over a long period of time. Hence the proposed method of classification will be helpful to doctors to determine the severity of PVC in a patient. Principal Component Analysis (PCA) and a simple classifier have been used in addition to the specially developed wavelet transform. The proposed wavelet has been designed using multiple Gaussian functions which when summed up looks similar to that of a normal ECG. The number of Gaussians used depends on the number of peaks present in a normal ECG. The developed wavelet satisfied all the properties of a traditional continuous wavelet. The new wavelet was optimized using genetic algorithm (GA). ECG records from Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) database have been used for validation. Out of the 8694 ECG cycles used for evaluation, the classification algorithm responded with an accuracy of 97.77%. In order to compare the performance of the new wavelet, classification was also performed using the standard wavelets like morlet, meyer, bior3.9, db5, db3, sym3 and haar. The new wavelet outperforms the rest

Fractionation and bioavailability of phosphorus in a tropical estuary, Southwest India

Phosphorus fractionation was employed to find the bioavailability of phosphorus and its seasonal variations in the Panangad region of Cochin estuary, the largest estuarine system in the southwest coast of India. Sequential extraction of the surficial sediments using chelating agents was taken as a tool for this. Phosphate in the water column showed seasonal variations, with high values during the monsoon months, suggesting external runoff. Sediment texture was found to be the main factor influencing the spatial distribution of the geochemical parameters in the study region. Similarly, total phosphorus also showed granulometric dependence and it ranged between 319.54 and 2,938.83 μg/g. Calcium-bound fraction was the main phosphorus pool in the estuary. Significant spatial variations were observed for all bioavailable fractions; iron-bound inorganic phosphorus (5.04–474.24 μg/g), calcium-bound inorganic phosphorus (11.16–826.09 μg/g), and acidsoluble organic phosphorus (22.22–365.86 μg/g). Among the non-bioavailable phosphorus, alkalisoluble organic fraction was the major one (51.92– 1,002.45 μg/g). Residual organic phosphorus was K. R. Renjith (B) · N. Chandramohanakumar · M. M. Joseph Department of Chemical Oceanography, School of Marine Sciences, Cochin University of Science and Technology, Kochi 682016, Kerala, India e-mail: renjithaqua@gmail.com comparatively smaller fraction (3.25–14.64% of total). The sandy and muddy stations showed distinct fractional composition and the speciation study could endorse the overall geochemical character. There could be buffering of phosphorus, suggested by the increase in the percentage of bioavailable fractions during the lean premonsoon period, counteracting the decreases in the external loads. Principal component analysis was employed to find the possible processes influencing the speciation of phosphorus in the study region

ToxicMetals Enrichment in the Surficial Sediments of a Eutrophic Tropical Estuary (Cochin Backwaters, Southwest Coast of India)

Concentrations and distributions of trace metals (Cd, Co, Cr, Cu, Fe, Mn, Ni, Pb, and Zn) in surficial sediments of the Cochin backwaters were studied during both monsoon and pre-monsoon periods. Spatial variations were in accordance with textural charaterstics and organic matter content. A principal component analysis distinguished three zones with different metal accumulation capacity: (i) highest levels in north estuary, (ii) moderate levels in central zone, and (iii) lowest levels in southern part. Trace metal enrichments are mainly due to anthropogenic contribution of industrial, domestic, and agricultural effluents, whose effect is enhanced by settling of metals due to organic flocculation and inorganic precipitation associated with salinity changes. Enrichments factors using Fe as a normalizer showed that metal contamination was the product of anthropogenic activities. An assessment of degree of pollution-categorized sediments as moderately polluted with Cu and Pb, moderately-to-heavily polluted with Zn, and heavily-to-extremely polluted with Cd. Concentrations at many sites largely exceed NOAA ERL (e.g., Cu, Cr, and Pb) or ERM (e.g., Cd, Ni, and Zn). This means that adverse effects for benthic organisms are possible or even highly probable.