A novel method for the classification of Alzheimer's disease from normal controls using magnetic resonance imaging

Alzheimer's disease (AD) is the most prevalent form of dementia. Although fewer people, who suffer from AD are correctly and promptly diagnosed, due to a lack of knowledge of its cause and unavailability of treatment, AD is more manageable if the symptoms of mild cognitive impairment (MCI) are in an early stage. In recent years, computer‐aided diagnosis has been widely used for the diagnosis of AD. The main motive of this paper is to improve the classification and prediction accuracy of AD. In this paper, a novel approach is developed to classify MCI, normal control (NC), and AD using structural magnetic resonance imaging (sMRI) from the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset (50 AD, 50 NC, 50 MCI subjects). FreeSurfer is used to process these MRI data and obtain cortical features such as volume, surface area, thickness, white matter (WM), and intrinsic curvature of the brain regions. These features are modified by normalizing each cortical region's features using the absolute maximum value of that region's features from all subjects in each group of MCI, NC, and AD independently. A total of 420 features are obtained. To address the curse of dimensionality, the obtained features are reduced to 30 features using a sequential feature selection technique. Three classifiers, namely the twin support vector machine (TSVM), least squares TSVM (LSTSVM), and robust energy‐based least squares TSVM (RELS‐TSVM), are used to evaluate the classification accuracy from the obtained features. Five‐fold and 10‐fold cross‐validation are used to validate the proposed method. Experimental results show an accuracy of 100% for the studied database. The proposed approach is innovative due to its higher classification accuracy compared to methods in the existing literature.     

Confidence voting method ensemble applied to off-line signature verification

In this paper, a new approximation to off-line signature verification is proposed based on two-class classifiers using an expert decisions ensemble. Different methods to extract sets of local and a global features from the target sample are detailed. Also a normalization by confidence voting method is used in order to decrease the final equal error rate (EER). Each set of features is processed by a single expert, and on the other approach proposed, the decisions of the individual classifiers are combined using weighted votes. Experimental results are given using a subcorpus of the large MCYT signature database for random and skilled forgeries. The results show that the weighted combination outperforms the individual classifiers significantly. The best EER obtained were 6.3 % in the case of skilled forgeries and 2.31 % in the case of random forgeries.     

IR and Raman studies and effect of γ radiation on crystallization of some lead borate glasses containing Al2O3

IR and Raman spectra of glass ceramics based on PbO-Cr₂O₃-B₂O₃glass composition system have been studied. The bands characteristic of BO₃. and BO₄ functional groups are present in all the samples. An incorporation of Al₂O₃(up to 5 mol%) in the initial glass composition considerably changes the glass network structure and relative concentrations of BO₃ and BO₄ groups. The composition 50 PbO-20 Cr₂O₃-25 B₂O₃-5 Al₂O₃(in mol%) reveals a maximum fraction of boron in the BO₄ group. A sample of this composition heat treated at 850° C for 25 h shows a maximum crystallization fraction with Pb₂O · CrO₄ as a prominent crystalline phase. The glasses irradiated with rays inhibit the crystallization into the Pb₂O · CrO₄ phase. They also show relatively smaller thermal conductivity.     

2-DOF vibratory gyroscope fabricated by SU-8 based UV-LIGA process

This paper reports fabrication of 2-DOF vibratory gyroscope using SU-8 based UV-LIGA process. The device structure is designed to be symmetrical in order to match the resonance frequencies of drive and sense mode oscillators and also to minimize their relative temperature dependent drift. The overall arrangement is such that the two vibration modes do not affect each other and therefore, mechanical decoupling is achieved which helps in minimizing bias drift. The design is optimized to be compatible with the UV-LIGA process having 10 μm thick electroformed nickel as structural layer. Photolithography to create 11 μm thick SU-8 molds for electroforming sacrificial copper and structural nickel layer is optimized using multiple exposure technique that ensures near vertical side walls. Since the highly cross-linked SU-8 remaining after development is difficult to remove reliably from high aspect ratio structures without damage or alteration to the electroformed metals, a 2.45 GHz MW plasma etching process is developed with CF₄/O₂ mixes. The fabricated device is checked for off-plane misalignment between the stationary and movable comb fingers using white light interferometry and it is found to be almost negligible. Also, the prototype device is characterized for amplitude and phase spectral responses using Polytec MSA-500 Micro System Analyzer. The drive and sense mode resonance frequencies are observed at 7.3 and 7.1 kHz respectively against the mode matched designed frequency of 7.5 kHz.     

Epileptic seizure classification in EEG signals using second-order difference plot of intrinsic mode functions

Epilepsy is a neurological disorder which is characterized by transient and unexpected electrical disturbance of the brain. The electroencephalogram (EEG) is a commonly used signal for detection of epileptic seizures. This paper presents a new method for classification of ictal and seizure-free EEG signals. The proposed method is based on the empirical mode decomposition (EMD) and the second-order difference plot (SODP). The EMD method decomposes an EEG signal into a set of symmetric and band-limited signals termed as intrinsic mode functions (IMFs). The SODP of IMFs provides elliptical structure. The 95% confidence ellipse area measured from the SODP of IMFs has been used as a feature in order to discriminate seizure-free EEG signals from the epileptic seizure EEG signals. The feature space obtained from the ellipse area parameters of two IMFs has been used for classification of ictal and seizure-free EEG signals using the artificial neural network (ANN) classifier. It has been shown that the feature space formed using ellipse area parameters of first and second IMFs has given good classification performance. Experimental results on EEG database available by the University of Bonn, Germany, are included to illustrate the effectiveness of the proposed method.     

Hierarchical abnormal event detection by real time and semi-real time multi-tasking video surveillance system

In this paper, we describe how to detect abnormal human activities taking place in an outdoor surveillance environment. Human tracks are provided in real time by the baseline video surveillance system. Given trajectory information, the event analysis module will attempt to determine whether or not a suspicious activity is currently being observed. However, due to real-time processing constrains, there might be false alarms generated by video image noise or non-human objects. It requires further intensive examination to filter out false event detections which can be processed in an off-line fashion. We propose a hierarchical abnormal event detection system that takes care of real time and semi-real time as multi-tasking. In low level task, a trajectory-based method processes trajectory data and detects abnormal events in real time. In high level task, an intensive video analysis algorithm checks whether the detected abnormal event is triggered by actual humans or not.     

The effect of nanoclays on the nucleation,crystallization, and melting mechanisms of isotactic polypropylene

The influence of organomodified nanoclay (montmorillonite) on the crystallization and melting mechanisms of isotactic polypropylene (iPP) was studied. Films of both neat polymer and clay nanocomposites were prepared after molecular weight optimization through melt extrusion. Products exhibited the tactoidlike morphology since no compatibilizers were used. The effect of introduction of nanoclay within the polymer was studied through isothermal crystallization and linear heating. The results indicated that low nanoclay concentrations induce the formation of the β‐crystalline structure, its formation being inhibited with high nanoclay contents. Dynamic nonisothermal bulk crystallization experiments indicated that nanoclays act as nucleating agents of iPP. Isothermal, bulk crystallization studies indicated that the crystallization process (induction time and crystallization kinetics) is proportionally accelerated by the nanoclay presence. There was also an accelerated formation of secondary crystallization when nanoclays were present in high concentrations. POLYM. ENG. SCI., 47:1889–1897, 2007. © 2007 Society of Plastics Engineers     

EFFECT OF CROSS FLOW ON THE SPRAY CHARACTERISTICS OF AN INDUSTRIAL FEED NOZZLE

The spray characteristics of a scaled-down version of an industrial feed nozzle are studied in the presence of a cross flow. Aerated liquid nitrogen is injected through the nozzle to generate the spray. The aeration rate is low and held constant, while two different liquid flow rates are used to produce the spray. A nonuniform wind profile is chosen to represent the cross flow condition. The droplet diameter and velocity measurements are acquired using a phase-Doppler particle analyzer. The results of the present study indicate that the spray momentum flux determines the extent of the jet bending. The droplets are accelerated significantly in the initial jet region as a result of flashing. However, further downstream of the nozzle, the vaporization of the droplets is considered to be negligible. The size-velocity correlation changes significantly for the case where the spray is shifted due to the cross flow.     

Changes in serum lipids in rats treated with oral cooper

Disturbances in lipid metabolism during copper deficiency in rats are well recognized. Copper deficiency is associated with the spontaneous retention of hepatic iron. Previous studies have reported that hypercholesterolemia and hypertriglyceridemia are associated with elevated hepatic iron concentrations in copper deficient rats. There was a direct relationship between the magnitude of blood lipids and the concentration of hepatic iron. Based on these data, it has been hypothesized that iron was responsible for the development of lipemia of copper deficiency. In this study was determined the effect of increasing doses of Cu(10, 20 and 50 ppm) in the diet, on the serum total lipids, total cholesterol, triglycerides (triacylglicerols), phospholipids, non-esterified fatty acids (NEFA) and liver iron and zinc concentrations in normal rats. The results were compared with normal rats that received a balanced diet containing 0.6 and 6 ppm of Cu, respectively. The results show that Cu-supplement diminished the cholesterol and triglyceride serum levels, increased the level of phospholipids, NEFA and concomitantly decreased the hepatic concentrations of Fe and Zn. There was a statistically significant (p < 0.05) simple correlation between triglycerides and liver Fe (r = 0.917; R2 = 64.03%), cholesterol and liver Zn (r = 0.872; R2 = 76.07%), cholesterol and liver Fe (r = 0.995; R2 = 99.10%), liver Fe and liver Cu (r = -0.612), liver Fe and liver Zn (r = 0.837), liver Cu and liver Zn (r = -0.612), and serum triglycerides and liver Zn (r = 0.967). The mechanism(s) by which Fe and Zn determine these changes is not known; none of the enzymes that act in cholesterol and triglyceride metabolism and biosynthesis require Fe and/or Zn. The increase of NEFA is due to changes in the process of lipolysis and re-esterification of the fatty acids in blood. However, additional studies are needed for the precise mechanisms of this interrelationships to be clarified.