Automated Artificial Intelligence Empowered White Blood Cells ClassificationModel

White blood cells (WBC) or leukocytes are a vital component of the blood which forms the immune system, which is accountable to fight foreign elements. The WBC images can be exposed to different data analysis approaches which categorize different kinds of WBC. Conventionally, laboratory tests are carried out to determine the kind of WBC which is erroneous and time consuming. Recently, deep learning (DL) models can be employed for automated investigation of WBC images in short duration. Therefore, this paper introduces an Aquila Optimizer with Transfer Learning based Automated White Blood Cells Classification (AOTL-WBCC) technique. The presented AOTL-WBCC model executes data normalization and data augmentation process (rotation and zooming) at the initial stage. In addition, the residual network (ResNet) approach was used for feature extraction in which the initial hyperparameter values of the ResNet model are tuned by the use of AO algorithm. Finally, Bayesian neural network (BNN) classification technique has been implied for the identification of WBC images into distinct classes. The experimental validation of the AOTL-WBCC methodology is performed with the help of Kaggle dataset. The experimental results found that the AOTL-WBCC model has outperformed other techniques which are based on image processing and manual feature engineering approaches under different dimensions.     

Segmented Drain Engineered Tunnel Field Effect Transistor for Suppression of Ambipolarity

Silicon - In this paper, a new Si0.6Ge0.4/Si heterostructure tunneling field-effect transistor with segmented drain (SiGe/Si SD TFET) is proposed and simulated by Silvaco ATLAS simulator. The drain...     

Nonlinear Dynamic System Identification of ARX Model for Speech Signal Identification

System Identification becomes very crucial in the field of nonlinear and dynamic systems or practical systems. As most practical systems don’t have prior information about the system behaviour thus, mathematical modelling is required. The authors have proposed a stacked Bidirectional Long-Short Term Memory (Bi-LSTM) model to handle the problem of nonlinear dynamic system identification in this paper. The proposed model has the ability of faster learning and accurate modelling as it can be trained in both forward and backward directions. The main advantage of Bi-LSTM over other algorithms is that it processes inputs in two ways: one from the past to the future, and the other from the future to the past. In this proposed model a backward-running Long-Short Term Memory (LSTM) can store information from the future along with application of two hidden states together allows for storing information from the past and future at any moment in time. The proposed model is tested with a recorded speech signal to prove its superiority with the performance being evaluated through Mean Square Error (MSE) and Root Means Square Error (RMSE). The RMSE and MSE performances obtained by the proposed model are found to be 0.0218 and 0.0162 respectively for 500 Epochs. The comparison of results and further analysis illustrates that the proposed model achieves better performance over other models and can obtain higher prediction accuracy along with faster convergence speed.     

Assessment of heat transfer in large parallel plates with a narrow gap maintained at a constant temperature

Investigations are conducted on electromagnetohydrodynamic (EMHD) flow and heat transfer in a third-grade fluid flowing through large parallel plates, which are maintained at constant temperatures. The impact of convective heat transmission is disregarded since the space between the plates is small. The influence of viscous dissipation is considered. Despite being addressed for Newtonian fluids, the conduction problem with the viscous dissipation effect is not examined in third-grade fluids for EMHD flow and heat transfer behavior. The least-square method is adopted to solve nondimensional, nonlinear momentum and energy conservation equations to get the dimensionless velocity, temperature distribution, and heat flux. Temperature and heat flux are investigated in relation to the third-grade fluid parameter, the Hartmann number, the electric field parameter, and the Brinkman number. The findings show a rise in the Brinkman number dramatically increases heat transfer from both walls, necessitating cooling of both plates. The heat flow from both walls increases as the parameters of third-grade fluid increases.     

Novel eco‐friendly biodegradable coir‐polyester amide biocomposites: Fabrication and properties evaluation

Biocomposites are prepared from a cheap, renewable natural fiber, coir (coconut fiber) as reinforcement with a biodegradable polyester amide (BAK 1095) matrix. In order to have better fiber‐matrix interaction the fibers are surface modified through alkali treatment, cyanoethylation, bleaching and vinyl grafting. The effects of different fiber surface treatments and fiber amounts on the performance of resulting bio‐composites are investigated. Among all modifications, cyanoethylated coir‐BAK composites show better tensile strength (35.50 MPa) whereas 7% methyl methacrylate grafted coir‐BAK composites show significant improvement in flexural strength (87.36 MPa). The remarkable achievement of the present investigation is that a low strength coir fiber, through optimal surface modifications, on reinforcement with BAK show an encouraging level of mechanical properties. Moreover, the elongation at break of BAK polymer is considerably reduced by the incorporation of coir fibers from nearly 400% (percent elongation of pure BAK) to 16‐24% (coir‐BAK biocomposites). SEM investigations show that surface modifications improve the fiber‐matrix adhesion. From biodegradation studies we find that after 52 days of soil burial, alkali treated and bleached coir‐BAK composites show significant weight loss. More than 70% decrease in flexural strength is observed for alkali treated coir‐BAK composites after 35 days of soil burial. The loss of weight and the decrease of flexural strength of degraded composites are more or less directly related.