An Optimized Neural Network with Bat Algorithm for DNA Sequence Classification

Recently, many researchers have used nature inspired metaheuristic algorithms due to their ability to perform optimally on complex problems. To solve problems in a simple way, in the recent era bat algorithm has become famous due to its high tendency towards convergence to the global optimum most of the time. But, still the standard bat with random walk has a problem of getting stuck in local minima. In order to solve this problem, this research proposed bat algorithm with levy flight random walk. Then, the proposed Bat with Levy flight algorithm is further hybridized with three different variants of ANN. The proposed BatLFBP is applied to the problem of insulin DNA sequence classification of healthy homosapien. For classification performance, the proposed models such as Bat levy flight Artificial Neural Network (BatLFANN) and Bat levy Flight Back Propagation (BatLFBP) are compared with the other state-of-the-art algorithms like Bat Artificial Neural Network (BatANN), Bat back propagation (BatBP), Bat Gaussian distribution Artificial Neural Network (BatGDANN). And Bat Gaussian distribution back propagation (BatGDBP), in-terms of means squared error (MSE) and accuracy. From the perspective of simulations results, it is show that the proposed BatLFANN achieved 99.88153% accuracy with MSE of 0.001185, and BatLFBP achieved 99.834185 accuracy with MSE of 0.001658 on WL5. While on WL10 the proposed BatLFANN achieved 99.89899% accuracy with MSE of 0.00101, and BatLFBP achieved 99.84473% accuracy with MSE of 0.004553. Similarly, on WL15 the proposed BatLFANN achieved 99.82853% accuracy with MSE of 0.001715, and BatLFBP achieved 99.3262% accuracy with MSE of 0.006738 which achieve better accuracy as compared to the other hybrid models.

     

Emotion Recognition from Occluded Facial Images Using Deep EnsembleModel

Facial expression recognition has been a hot topic for decades, but high intraclass variation makes it challenging. To overcome intraclass variation for visual recognition, we introduce a novel fusion methodology, in which the proposed model first extract features followed by feature fusion. Specifically, RestNet-50, VGG-19, and Inception-V3 is used to ensure feature learning followed by feature fusion. Finally, the three feature extraction models are utilized using Ensemble Learning techniques for final expression classification. The representation learnt by the proposed methodology is robust to occlusions and pose variations and offers promising accuracy. To evaluate the efficiency of the proposed model, we use two wild benchmark datasets Real-world Affective Faces Database (RAF-DB) and AffectNet for facial expression recognition. The proposed model classifies the emotions into seven different categories namely: happiness, anger, fear, disgust, sadness, surprise, and neutral. Furthermore, the performance of the proposed model is also compared with other algorithms focusing on the analysis of computational cost, convergence and accuracy based on a standard problem specific to classification applications.     

Classification of multi-lingual tweets,into multi-class model using Naïve Bayes and semi-supervised learning

Multimedia Tools and Applications - Twitter is a social media platform which has been proven to be a great tool for insights of emotions about products, policies etc. through a 280-character...     

Biological nitrogen and phosphorus removal and changes in microbial community structure in a membrane bioreactor: effect of different carbon sources

Bacterial community structures in four sequencing anoxic/anaerobic-aerobic membrane bioreactors (SAMs) that were fed with synthetic medium composed of different organic compounds in substrate as carbon source; acetate-dominant (acetate/propionate = 4/1), propionate-dominant (acetate/propionate = 1/4), glucose-dominant (glucose/acetate = 4/1) and methanol-dominant (methanol/acetate/propionate = 6/3/1) were analyzed by respiratory quinone profile and fluorescent in situ hybridization (FISH) techniques. The SAMs were operated at controlled pH range 7-8.5 and at constant temperature 25 degrees C. Total nitrogen (TN), total phosphorus (TP) and COD removal performances were also evaluated and compared. In addition, trans-membrane pressure was monitored to observe the impact of substrate composition on membrane fouling. The dominance of the mole fraction of ubiquinone (UQ-8) in the SAMs indicated dominance of the beta-subclass of Proteobacteria; however, its population comparatively decreased when the substrate was glucose dominant or methanol dominant. A relatively higher and stable enhanced biological phosphorus removal performance was observed when methanol-dominant substrate was used concurrently with an increase in the gamma-subclass of Proteobacteria. The population of the alpha-subclass of Proteobacteria slightly increased along with a decrease in phosphate removal activity when the substrate was glucose-dominant. Results from FISH analysis also supported the findings of the quinone profile. The trans-membrane pressure variation in the SAMs indicated that fouling was relatively rapid when propionate-dominant or methanol-dominant substrate was used and most stable when glucose-dominant substrate was used. A combination of methanol and acetate would be a better choice as an external carbon source when nutrients removals, as well as fouling, are considered in the membrane bioreactor- (MBR-) coupled biological nutrients removing (BNR) process.     

Generation of electrical energy using lead zirconate titanate (PZT-5A) piezoelectric material: Analytical,numerical and experimental verifications

Energy harvesting is the process of attaining energy from the external sources and transforming it into usable electrical energy. An analytical model of piezoelectric energy harvester has been developed to determine the output voltage across an electrical circuit when it is forced to undergo a base excitation. This model gives an easy approach to design and investigate the behavior of piezoelectric material. Numerical simulations have been carried out to determine the effect of frequency and loading on a Lead zirconate titanate (PZT-5A) piezoelectric material. It has been observed that the output voltage from the harvester increases when loading increases whereas its resonance frequency decreases. The analytical results were found to be in good agreement with the experimental and numerical simulation results.     

Efficiency and optimization of an annular fin with combined heat and mass transfer – An analytical solution

An analysis was carried out to study the efficiency of annular fin when subjected to simultaneous heat and mass transfer mechanisms. The temperature and humidity ratio differences are the driving forces for the heat and mass transfer, respectively. Analytical solutions are obtained for the temperature distribution over the fin surface when the fin is fully wet. The effect of the atmospheric pressure on the fin efficiency was also studied, in addition to fin optimum dimensions. It is demonstrated that the closed-form solutions for a dry-fin case presented in many text books are special cases for the solutions presented in this paper.     

Thermoeconomic considerations in the design and rating of two-phase heat exchangers

We discuss a closed-form model for thermoeconomic design and analysis of two-phase heat exchangers used as condensers and evaporators. The results are presented in terms of the optimum number of heat-transfer units (NTUs) as a function of the dimensionless unit-cost ratio and the exit-to-inlet absolute temperature ratio of the single-phase fluid. The sensitivities of various unit-cost parameters (UCPs) are presented. It is demonstrated that the selection of UCPs play a significant role in sizing heat exchangers.     

A comprehensive design and rating study of evaporative coolers and condensers. Part I. Performance evaluation

The mathematical models of evaporative fluid coolers and evaporative condensers are studied in detail to perform a comprehensive design and rating analysis. The mathematical models are validated using experimental as well as numerical data reported in the literature. These models are integrated with the fouling model presented in an earlier paper, using the experimental data on tube fouling. In this paper, we use the fouling model to investigate the risk based thermal performance of these evaporative heat exchangers. It is demonstrated that thermal effectiveness of the evaporative heat exchangers degrades significantly with time indicating that, for a low risk level (p=0.01), there is about 66.7% decrease in effectiveness for the given fouling model. Furthermore, it is noted that there is about 4.7% increase in outlet process fluid temperature of the evaporative fluid cooler. Also, a parametric study is performed to evaluate the effect of elevation and mass flow rate ratio on typical performance parameters such as effectiveness for rating calculations while surface area for design calculations.     

Tensile behavior of staple fiber yarns,part IV: experimental verification of predicted stress–strain curves

In this paper, specific stress–strain curves were predicted for viscose, cotton, and polyester yarns spun by ring and rotor technologies. The average fiber-specific stress–strain curves were used to predict yarn-specific stress–strain curves. The predicted yarn-specific stress–strain curves captured the experimental yarn-specific stress–strain curves well both in shape and position for the three studied yarn types. However, higher prediction error was observed relatively in polyester yarns due to more slippage of fibers in these yarns. All rotor yarns exhibited higher difference between experimental and predicted results which might be the result of the nature of the twist in rotor yarn.