Intelligent Firefly Algorithm Deep Transfer Learning Based COVID-19 Monitoring System

With the increasing and rapid growth rate of COVID-19 cases, the healthcare scheme of several developed countries have reached the point of collapse. An important and critical steps in fighting against COVID-19 is powerful screening of diseased patients, in such a way that positive patient can be treated and isolated. A chest radiology image-based diagnosis scheme might have several benefits over traditional approach. The accomplishment of artificial intelligence (AI) based techniques in automated diagnoses in the healthcare sector and rapid increase in COVID-19 cases have demanded the requirement of AI based automated diagnosis and recognition systems. This study develops an Intelligent Firefly Algorithm Deep Transfer Learning Based COVID-19 Monitoring System (IFFA-DTLMS). The proposed IFFA-DTLMS model majorly aims at identifying and categorizing the occurrence of COVID19 on chest radiographs. To attain this, the presented IFFA-DTLMS model primarily applies densely connected networks (DenseNet121) model to generate a collection of feature vectors. In addition, the firefly algorithm (FFA) is applied for the hyper parameter optimization of DenseNet121 model. Moreover, autoencoder-long short term memory (AE-LSTM) model is exploited for the classification and identification of COVID19. For ensuring the enhanced performance of the IFFA-DTLMS model, a wide-ranging experiments were performed and the results are reviewed under distinctive aspects. The experimental value reports the betterment of IFFA-DTLMS model over recent approaches.     

A magnetic bead-based DNA extraction and purification microfluidic device

This article introduces a novel magnetic bead-based DNA extraction and purification device using active magnetic mixing approach. Mixing and separation steps are performed using functionalised superparamagnetic beads suspended in cell lysis buffer in a circular chamber that is sandwiched between two external magnetic coils. Non-uniform nature of magnetic field causes temporal and spatial distribution of beads within the chamber. This process efficiently mixes the lysis buffer and whole blood in order to extract DNA from target cells. Functionalized surface of the magnetic beads then attract the exposed DNA molecules. Finally, DNA-attached magnetic beads are attracted to the bottom of the chamber by activating the bottom magnetic coil. DNA molecules are extracted from magnetic beads by washing and re-suspension processes. In this study, a circular PMMA microchamber, 25 μL in volume, 500 μm in depth and 8 mm in diameter was fabricated to purify DNA from spiked bacterial cell cultures into the whole blood sample using Promega Magazorb DNA extraction kit. The lysis efficiency was evaluated using a panel of Gram-positive (Bacillus subtilis) and Gram-negative (Escherichia coli) bacterial cells cultures into the blood sample to achieve approximately 100,000 copy levels inside the chip. Manufacturer’s standard extraction protocol was modified to a more simplified process suitable for chip-based extraction. The lysis step was performed using 5 min incubation at 56 °C followed by 5 min incubation at room temperature for binding process. Temperature rise was generated and maintained by the same external magnetic coils used for active mixing. The yield/purity and recovery levels of the extracted DNA were evaluated using quantitative UV spectrophotometer and real-time PCR assay, respectively. Real-time PCR results indicated efficient chip-based bacterial DNA extraction using modified extraction protocol comparable to the standard bench-top extraction process.     

Multirange multi-relaxation time Shan–Chen model with extended equilibrium

The work presents simulations with the multirange Shan–Chen model developed by Sbragaglia et al. (2007) [18], which improved the Shan–Chen model for the proper surface tension term. Also, by introducing the matrix collision operator and extended equilibrium density distribution function, the density ratio is increased from 100 to 160. The Multi-Relaxation Time (MRT) method attracted the attention of researchers due to several advantages, such as better stability, simulations with Prandtl number different from unity, and possibilities to improve the accuracy of the scheme compared with BGK Single Time Relaxation model. Our recent results have shown that the combination of MRT methods with multiphase flow models can improve the achievable gas–liquid density ratio.     

The performance of multiwavelets based OFDM system under different channel conditions

In wireless communication reception, the reliability of orthogonal frequency division multiplexing (OFDM) is limited because of the time-varying nature of the channel. This causes inter-carrier interference (ICI) and increases inaccuracies in channel tracking. This can effectively be avoided at the cost of power loss and bandwidth expansion by inserting a cyclic prefix guard interval before each block of parallel data symbols. However, this guard interval decreases the spectral efficiency of the OFDM system as the corresponding amount. Recently, it was found that based on Haar-orthonormal wavelets, discrete wavelet-based OFDM (DWT-OFDM) is capable of reducing the inter symbol interference (ISI) and ICI, which are caused by the loss in orthogonality between the carriers. DWT-OFDM can also support much higher spectrum efficiency than discrete Fourier-based OFDM (DFT-OFDM). In this paper the DFT-OFDM is replaced by Multiwavelets OFDM (DMWT-OFDM) in order to further reduce the level of interference and increase spectral efficiency. It is found that proposed Multiwavelet design achieves much lower bit error rates, increases signal to noise power ratio (SNR), and can be used as an alternative to the conventional OFDM. The proposed OFDM system was modeled tested, and its performance was found under different channel conditions.     

Analysis,modeling, and design of cascaded defected microstrip structure for planar circuits

In this article, two cascaded defected microstrip structures (CDMSs) are proposed to increase the effective inductance. So the cutoff frequencies of filters made by CDMSs can be controlled. The proposed CDMSs have wider stopband characteristic and sharper transition from passband to stopband than defected microstrip structure (DMS). To show the behavior variations of the effective inductance, the DMS and CDMSs have been analyzed, compared, and their design parameters are formulated. These parameters are necessary for a fast filter design procedure. Also, the models of DMS and CDMSs using the very simple lumped element forms are presented according to the physical parameters. The results of the proposed models have been compared with those obtained by full wave analysis. To verify the proposed DMS model, the comparison in response not only has been considered in amplitude but also in phase of all S‐parameters of proposed model and full wave analysis. It is obvious that the stopband is enhanced by periodically cascading the DMS. Surviving of EMC aspects between DMS, DGS, and CDMS is considered and compared. Finally, the theoretical results are validated by comparison with simulations of the structures and experimental results. The simulations from modeling results are found to be in good agreement with the full wave analysis and measurement results in the range of 0.5–35 GHz. © 2010 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2010.     

MobiEureka: an approach for enhancing the discovery of mobile web services

While several service discovery protocols and standards have been proposed for supporting service discovery from mobile devices, this remains a challenging problem. In many cases, mobile clients may discover services which they consider relevant but soon realize that such services are not completely usable on their mobile devices due to compatibility and interoperability issues. Without integrating device capabilities into the discovery process, or a device-aware mobile service discovery, it becomes extremely difficult to determine whether discovered services may or may not function properly within the device’s constraints. This paper introduces a solution known as MobiEureka, a mobile device-aware system for enhancing the discovery of mobile web services from mobile devices. Experimental validation, results, and analysis of the introduced ideas are discussed.     

Empirical comparison of three metrics suites for fault prediction in packages of object-oriented systems: A case study of Eclipse

Packages are important high-level organizational units for large object-oriented systems. Package-level metrics characterize the attributes of packages such as size, complexity, and coupling. There is a need for empirical evidence to support the collection of these metrics and using them as early indicators of some important external software quality attributes. In this paper, three suites of package-level metrics (Martin, MOOD and CK) are evaluated and compared empirically in predicting the number of pre-release faults and the number of post-release faults in packages. Eclipse, one of the largest open source systems, is used as a case study. The results indicate that the prediction models that are based on Martin suite are more accurate than those that are based on MOOD and CK suites across releases of Eclipse.