Data stream classification with novel class detection: a review,comparison and challenges

Knowledge and Information Systems - Developing effective and efficient data stream classifiers is challenging for the machine learning community because of the dynamic nature of data streams. As a...     

Spatial division networks for weakly supervised detection

Neural Computing and Applications - With only global image-level annotations, weakly supervised learning of deep convolutional neural networks has shown enough capacity in classification and...     

Resource-constrained FPGA implementation of YOLOv2

Neural Computing and Applications - Progress is being made to deploy convolutional neural networks (CNNs) into the Internet of Things (IoT) edge devices for handling image analysis tasks locally....     

Quantum Inspired Broadband Photonic Absorber: Potential Application as Solar Sail along with Mobility Analysis

Electromagnetic wideband absorption is still perceived as a critical and formidable challenge to address with an unambiguous photonic absorber. Subwavelength metamaterial (MM) unit cells with unique and controlled features have recently gained considerable interest. However, meta-atoms, generated using a quantum-inspired pattern distribution, are underwhelming in existing literature to design photonic absorbers and their potential application to manufacture solar sails is still quite uncommon. In this article, to create a flexible, polarization-insensitive, ultrathin, and broadband MM absorber, quantum interference pattern-inspired design is utilized. Herein, a novel approach to fabricating solar sails for the space exploration incorporates the proposed broadband photonic absorber rather than conventional reflectors. The quantum-inspired meta-absorber (QIMA) exhibits an absorption of over 91% for the visible domain, i.e., 380–800 nm under a conventional plane-polarized source. It is shown in the study that broadband absorbers are almost equivalent to excellent reflectors to design the solar sails in terms of the time-averaged force calculated by utilizing the Maxwell stress tensor method. Thus, the QIMA has the potential to be a viable alternative to reflectors in the design of futuristic solar sails for space exploration. The interference theory model is also utilized to assure the dependability of calculated data, and additionally, the standard AM1.5 solar spectrum is utilized to demonstrate the QIMA's solar-harvesting potentiality.     

Power quality diagnosis using time frequency analysis and rule based techniques

Diagnosing a power quality disturbance means identifying the type and cause of the disturbance. Fast diagnosis of power quality disturbances is important so as to assist network operators in performing counter measures and implementing suitable power quality mitigation actions. In this study a novel method for performing power quality diagnosis is presented by using the S-transform and rule based classification techniques. The proposed power quality diagnosis method was evaluated for its functionality in detecting the type of short duration voltage disturbances and identifying the cause of the disturbances which may be due to permanent or non permanent faults. Based on the results, this new method has the potential to be used in the existing real time power quality monitoring system in Malaysia to expedite the diagnosis on the recorded voltage disturbances.     

Generalized Regression Neural Networks and Feed Forward Neural Networks for prediction of scour depth around bridge piers

In this study, Generalized Regression Neural Networks (GRNN) and Feed Forward Neural Networks (FFNN) approaches are used to predict the scour depth around circular bridge piers. Hundred and sixty five data collected from various experimental studies, are used to predict equilibrium scour depth. The model consisting of the combination of dimensional data involving the input variables is constructed. The performance of the models in training and testing sets are compared with observations. Then, the model is also tested by Multiple Linear Regression (MLR) and empirical formula. The results of all approaches are compared in order to get more reliable comparison. The results indicated that GRNN can be applied successfully for prediction of scour depth around circular bridge piers.     

A method for real power transfer allocation using multivariable regression analysis

A multivariable regression (MVR) approach is proposed to identify the real power transfer between generators and loads. Based on solved load flow results, it first uses modified nodal equation method (MNE) to determine real power contribution from each generator to loads. Then, the results of MNE method and load flow information are utilized to determine suitable regression coefficients using MVR model to estimate the power transfer. The 25-bus equivalent system of south Malaysia is utilized as a test system to illustrate the effectiveness of the MVR output compared to that of the MNE method. The error of the estimate of MVR method ranges from 0.001 4 to 0.007 9. Furthermore, when compared to MNE method, MVR method computes generator contribution to loads within 26.40 ms whereas the MNE method takes 360 ms for the calculation of same real power transfer allocation. Therefore, MVR method is more suitable for real time power transfer allocation.     

Rapid Detection of Wheat Blast Pathogen Magnaporthe oryzae Triticum Pathotype Using Genome-Specific Primers and Cas12a-mediated Technology

Wheat blast, caused by the fungus Magnaporthe oryzae Triticum (MoT) pathotype, is a devastating disease persistent in South America and Bangladesh. Since MoT generally fails to cause visual symptoms in wheat until the heading stage when the infection would have advanced, disease control by fungicide application solely based on the detection of visual symptoms is ineffective. To develop an accurate and sensitive method to detect MoT at the seedling and vegetative stages for disease control, we sequenced the genomes of two MoT isolates from Brazil and identified two DNA fragments, MoT-6098 and MoT-6099, that are present in the MoT genome but not in the genome of the rice-infecting Magnaporthe oryzae Oryzae (MoO) pathotype. Using polymerase chain reaction (PCR), we confirmed the specificity of the two markers in 53 MoT and MoO isolates from South America and Bangladesh. To test the efficiency of the two markers, we first established a loop-mediated isothermal amplification (LAMP) method to detect MoT at isothermal conditions, without the use of a PCR machine. Following this, we used the Cas12a protein and guide RNAs (gRNAs) to target the MoT-6098 and MoT-6099 sequences. The activated Cas12a showed indiscriminate single-stranded deoxyribonuclease (ssDNase) activity. We then combined target-dependent Cas12a ssDNase activation with recombinase polymerase amplification (RPA) and nucleic acid lateral flow immunoassay (NALFIA) to develop a method that accurately, sensitively, and cost-effectively detects MoT-specific DNA sequences in infected wheat plants. This novel technique can be easily adapted for the rapid detection of wheat blast and other important plant diseases in the field.     

Novel Organometallic Aromatic Azo Polyesters Based on Ferrocene

Some ferrocene containing aromatic azo polyesters were prepared by condensing 1,1-ferrocenedicarbonyl chloride with different azo groups containing aromatic diols, which were synthesized by diazotization coupling reaction from aromatic diamines. The polymeric products were separated as two portions on the basis of their solubility and subsequently characterized by their elemental analysis and FTIR spectral studies. Thermal properties of the products were measured by differential scanning calorimetry and thermogravimetry and the activation energies of pyrolysis were calculated using Horowitz and Metzger's method. The molecular weights of the soluble portions were determined by gel permeation chromatography (GPC) and these portions were also characterized by their inherent viscosities and UV-Vis spectroscopic studies.     

Static and dynamic compressive properties of polypropylene/zinc oxide nanocomposites

The effect of strain rate is widely recognized as an essential factor that influences the mechanical properties of polymer matrix composites. Despite its importance, no previous work has been reported on the high‐strain rate behavior of polypropylene/zinc oxide nanocomposites. Based on this, static and dynamic compression properties of polypropylene/zinc oxide nanocomposites, with particle contents of 1%, 3%, and 5% by weight, were successfully studied at different strain rates (i.e., 0.01 s^?1, 0.1 s^?1, 650 s^?1, 900 s^?1, and 1100 s^?1) using a universal testing machine and a split Hopkinson pressure bar apparatus. For standardization, approximately 24 nm of zinc oxide nanoparticles were embedded into polypropylene matrix for each of the tested polypropylene/zinc oxide nanocomposites. Results show that the yield strength, the ultimate strength, and the stiffness properties, of polypropylene/zinc oxide nanocomposites, were greatly affected by both particle loading and applied strain rate. Furthermore, the rate sensitivity and the absorbed energy of all tested specimens showed a positive increment with increasing strain rate, whereas the thermal activation volume showed a contrary trend. In addition, the fractographic analysis and particle dispersion of all composite specimens were successfully obtained using a field emisission scanning electron microscopy. POLYM. ENG. SCI., 54:949–960, 2014. © 2013 Society of Plastics Engineers