Inverse random under sampling for class imbalance problem and its application to multi-label classification

In this paper, a novel inverse random under sampling (IRUS) method is proposed for the class imbalance problem. The main idea is to severely under sample the majority class thus creating a large number of distinct training sets. For each training set we then find a decision boundary which separates the minority class from the majority class. By combining the multiple designs through fusion, we construct a composite boundary between the majority class and the minority class. The proposed methodology is applied on 22 UCI data sets and experimental results indicate a significant increase in performance when compared with many existing class-imbalance learning methods. We also present promising results for multi-label classification, a challenging research problem in many modern applications such as music, text and image categorization.     

Study on the common criteria methodology for secure ubiquitous environment construction

The ubiquitous environment has been developed since the extension of IT technology. The term ‘Ubiquitous’ is referred firstly by Mark Weiser, which means the user based environment that provides network service ‘any time, anywhere’. In the ubiquitous environment, the computing environment should have the device that recognizes the user and the environment. But there is not a verification process when dealing in sensitive information, and it may cause serious errors or malfunction. In order to complement the problem, members of the CCRA utilized CC(Common Criteria) to build up an assessment system and create a secured ubiquitous environment.     

Sol–gel preparation of boron-containing cordierite Mg2(Al4−xBx)Si5O18 and its crystallization

Five cordierite-based powders were investigated regarding their thermal and crystallization behaviors. The powders were obtained from amorphous gels having nominal compositions of 2Mg : xAl : (4 − x)B : 5Si where x = 4 down to 0. Thermal gravimetry analysis of the dry gels showed some absorbed water and decomposition of organic ligands in addition to network condensation. Gradual substitution of B for Al in the dried gel powders showed a new band in their infrared spectra corresponding to triangular BO₃, whereas the bands corresponding to Al vanished. This also showed a noticeable effect on the crystallization trends, type and stability of cordierite. Cordierite crystallized in samples of B/Al ratio up to 1 while protoenstatite predominated in samples of higher B/Al ratios. In addition, some silica minerals, with little amorphous phase, were formed. Incorporation of boron and increase in temperature enhanced the transformation of γ cordierite to its form.     

Diversity improvement estimation from rain Radar databases using maximum likelihood estimation

This research examines route diversity as a fade mitigation technique in the presence of rain, for terrestrial microwave links. The improvement in availability due to diversity depends upon the complex spatio-temporal properties of rainfall. To produce a general model to predict the advantage due to route diversity it is necessary to be able to predict the correlation of rain attenuation on arbitrary pairs of microwave links. This is achieved by examination of a database of radar derived rain rate fields. Given a representative sample of rain field images, the joint rain attenuation statistics of arbitrary configurations of terrestrial links can be estimated. Existing rain field databases often yield very small numbers of high joint attenuation events. Consequently, estimates of the probability of joint high attenuation events derived from ratios of the number of occurrences can be highly inaccurate. This paper assumes that pairs of terrestrial microwave links have joint rain attenuation distributions that are bi-lognormally distributed. Four of the five distribution parameters can be estimated from ITU-R models. A maximum likelihood estimation (MLE) method is used to estimate the fifth parameter, i.e., the covariance or correlation. The predicted diversity statistics vary smoothly and yield plausible extrapolations into low probability situations.     

An efficient and robust integration technique for applied random vibration analysis

The mode-based finite element formulation of the equations of motion is usually adopted for linear random vibration analysis (RVA). In general, the RVA of large systems requires a large number of numerical integrations which is very time-consuming for a reasonable level of desired accuracy. Moreover, conventional numerical integration methods may fail to converge when the integrands are highly oscillatory due to slow propagation velocities. In this paper, a robust general-purpose RVA integration technique which can overcome these drawbacks is presented. Multi-point base and nodal excitations including wave passage effect and frequency-independent spatial correlation can be taken into account in the analysis. The proposed technique is based on the closed-form solutions for polynomial-type power spectral density functions and has been verified to be efficient and accurate for many engineering problems. This paper describes the implementation details, presents two examples taken from engineering applications and demonstrates the dramatic time-saving in the computation compared to numerical integration solutions. Response statistics, such as standard deviation of structural responses, are computed and displayed over the entire structures for these examples.     

Electric-field induced fluctuations in laser generated plasma plume

The effect of an external electric field on laser-generated plasma has been studied. It is observed that the laser-generated plasma can be used for the ignition of a spark in the presence of a low voltage external electric field. An eight-fold emission intensity enhancement in Cu Ⅰ spectral lines are measured as compared to the signal intensity in the absence of an external electric field.The plasma parameters remain the same initially, up to a few microseconds after the generation of plasma, and this feature makes it more interesting for the quantitative analysis of any sample using laser induced breakdown spectroscopy(LIBS). In the presence of an external electric field,fluctuations(contraction and expansion) in the laser-generated plasma are observed which increase the plasma decay time and consequently result in enhanced signal intensity.     

Highly Functional TNTs with Superb Photocatalytic,Optical, and Electronic Performance Achieving Record PV Efficiency of 10.1% for 1D‐Based DSSCs

Different nanostructures of TiO₂ play an important role in the photocatalytic and photoelectronic applications. TiO₂ nanotubes (TNTs) have received increasing attention for these applications due to their unique physicochemical properties. Focusing on highly functional TNTs (HF‐TNTs) for photocatalytic and photoelectronic applications, this study describes the facile hydrothermal synthesis of HF‐TNTs by using commercial and cheaper materials for cost‐effective manufacturing. To prove the functionality and applicability, these TNTs are used as scattering structure in dye‐sensitized solar cells (DSSCs). Photocatalytic, optical, Brunauer‐Emmett‐Teller (BET), electrochemical impedance spectrum, incident‐photon‐to‐current efficiency, and intensity‐modulated photocurrent spectroscopy/intensity‐modulated photovoltage spectroscopy characterizations are proving the functionality of HF‐TNTs for DSSCs. HF‐TNTs show 50% higher photocatalytic degradation rate and also 68% higher dye loading ability than conventional TNTs (C‐TNTs). The DSSCs having HF‐TNT and its composite‐based multifunctional overlayer show effective light absorption, outstanding light scattering, lower interfacial resistance, longer electron lifetime, rapid electron transfer, and improved diffusion length, and consequently, J _SC, quantum efficiency, and record photoconversion efficiency of 10.1% using commercial N‐719 dye is achieved, for 1D‐based DSSCs. These new and highly functional TNTs will be a concrete fundamental background toward the development of more functional applications in fuel cells, dye‐sensitized solar cells, Li‐ion batteries, photocatalysis process, ion‐exchange/adsorption process, and photoelectrochemical devices.     

Adsorption of dyes from aqueous solutions on activated charcoal

Adsorption of industrially important dyes namely bromophenol blue, alizarine red-S, methyl blue, methylene blue, eriochrome black-T, malachite green, phenol red and methyl violet from aqueous media on activated charcoal has been investigated. The effect of shaking time, pH and temperature on the adsorption behaviour of these dyes has been studied. It was noted that adsorption of all the dyes on activated charcoal decreases with an increase in the pH and the temperature. The adsorption isotherms at different temperatures were found to be of L-type. Adsorption data was fitted to Freundlich, BET and Langmuir isotherms and various adsorption parameters have been calculated. The thermodynamic parameters such as DeltaG, DeltaH and DeltaS were calculated from the slopes and intercepts of the linear variation of lnK against 1/T, where K is the adsorption coefficient obtained from Langmuir equation, was used. The calculated values for the heat of adsorption and the free energy indicate that adsorption of dyes is favored at low temperatures and the dyes are chemisorbed on activated charcoal.     

Autonomous Parking-Lots Detection with Multi-Sensor Data Fusion Using Machine Deep Learning Techniques

The rapid development and progress in deep machine-learning techniques have become a key factor in solving the future challenges of humanity. Vision-based target detection and object classification have been improved due to the development of deep learning algorithms. Data fusion in autonomous driving is a fact and a prerequisite task of data preprocessing from multi-sensors that provide a precise, well-engineered, and complete detection of objects, scene or events. The target of the current study is to develop an in-vehicle information system to prevent or at least mitigate traffic issues related to parking detection and traffic congestion detection. In this study we examined to solve these problems described by (1) extracting region-of-interest in the images (2) vehicle detection based on instance segmentation, and (3) building deep learning model based on the key features obtained from input parking images. We build a deep machine learning algorithm that enables collecting real video-camera feeds from vision sensors and predicting free parking spaces. Image augmentation techniques were performed using edge detection, cropping, refined by rotating, thresholding, resizing, or color augment to predict the region of bounding boxes. A deep convolutional neural network F-MTCNN model is proposed that simultaneously capable for compiling, training, validating and testing on parking video frames through video-camera. The results of proposed model employing on publicly available PK-Lot parking dataset and the optimized model achieved a relatively higher accuracy 97.6% than previous reported methodologies. Moreover, this article presents mathematical and simulation results using state-of-the-art deep learning technologies for smart parking space detection. The results are verified using Python, TensorFlow, OpenCV computer simulation frameworks.