Improving Alzheimer's Disease Classification in Brain MRI Images Using a Neural Network Model Enhanced with PCA and SWLDA.

The examination of Alzheimer's disease (AD) using adaptive machine learning algorithms has unveiled promising findings. However, achieving substantial credibility in medical contexts necessitates a combination of notable accuracy, minimal processing time, and universality across diverse populations. Therefore, we have formulated a hybrid methodology in this study to classify AD by employing a brain MRI image dataset. We incorporated an averaging filter during preprocessing in the initial stage to reduce extraneous details. Subsequently, a combined strategy was utilized, involving principal component analysis (PCA) in conjunction with stepwise linear discriminant analysis (SWLDA), followed by an artificial neural network (ANN). SWLDA employs a combination of forward and backward recursion methods to choose a restricted set of features. The forward recursion identifies the most interconnected features based on partial Z-test values. Conversely, the backward recursion method eliminates the least correlated features from the same feature space. After the extraction and selection of features, an optimized artificial neural network (ANN) was utilized to differentiate the various classes of AD. To demonstrate the significance of this hybrid approach, we utilized publicly available brain MRI datasets using a 10-fold cross-validation strategy. The proposed method excelled over existing state-of-the-art systems, attaining weighted average recognition rates of 99.35% and 96.66%, respectively, across all the datasets.

Photonic crystal nanostructure as a photodetector for NaCl solution monitoring: theoretical approach.

In this research, we have a theoretical simple and highly sensitive sodium chloride (NaCl) sensor based on the excitation of Tamm plasmon resonance through a one-dimensional photonic crystal structure. The configuration of the proposed design was, [prism/gold (Au)/water cavity/silicon (Si)/calcium fluoride (CaF2)10/glass substrate]. The estimations are mainly investigated based on both the optical properties of the constituent materials and the transfer matrix method as well. The suggested sensor is designed for monitoring the salinity of water by detecting the concentration of NaCl solution through near-infrared (IR) wavelengths. The reflectance numerical analysis showed the Tamm plasmon resonance. As the water cavity is filled with NaCl of concentrations ranging from 0 g l-1 to 60 g l-1, Tamm resonance is shifted towards longer wavelengths. Furthermore, the suggested sensor provides a relatively high performance compared to its photonic crystal counterparts and photonic crystal fiber designs. Meanwhile, the sensitivity and detection limit of the suggested sensor could reach the values of 24 700 nm per RIU (0.576 nm (g l)-1) and 0.217 g l-1, respectively. Therefore, the suggested design could be of interest as a promising platform for sensing and monitoring NaCl concentrations and water salinity as well.

Experimental evaluation of fracture properties of bovine hip cortical bone using elastic-plastic fracture mechanics.

BACKGROUND: Understanding the fracture mechanics of bone is very important in both the medical and bioengineering field. Bone is a hierarchical natural composite material of nanoscale collagen fibers and inorganic material. OBJECTIVE: This study investigates and presents the fracture toughness of bovine cortical bone by using elastic plastic fracture mechanics. METHODS: The J-integral was used as a parameter to calculate the energies utilized in both elastic deformation (Jel) and plastic deformation (Jpl) of the hipbone fracture. Twenty four different types of specimens, i.e. longitudinal compact tension (CT) specimens, transverse CT specimens, and also rectangular unnotched specimens for tension in longitudinal and transverse orientation, were cut from the bovine hip bone of the middle diaphysis. All CT specimens were prepared according to the American Society for Testing and Materials (ASTM) E1820 standard and were tested at room temperature. RESULTS: The results showed that the average total J-integral in transverse CT fracture specimens is 26% greater than that of longitudinal CT fracture specimens. For longitudinal-fractured and transverse-fractured cortical specimens, the energy used in the elastic deformation was found to be 2.8-3 times less than the energy used in the plastic deformation. CONCLUSION: The findings indicate that the overall fracture toughness measured using the J-integral is significantly higher than the toughness calculated by the stress intensity factor. Therefore, J-integral should be employ to compute the fracture toughness of cortical bone.

Antibiotic-Loaded Psyllium Husk Hemicellulose and Gelatin-Based Polymeric Films for Wound Dressing Application.

Wound infections are one of the major reasons for the delay in the healing of chronic wounds and can be overcome by developing effective wound dressings capable of absorbing exudate, providing local antibiotic release, and improving patient comfort. Arabinoxylan (AX) is a major hemicellulose present in psyllium seed husk (PSH) and exhibits promising characteristics for developing film dressings. Herein, AX-gelatin (GL) films were prepared by blending AX, gelatin (GL), glycerol, and gentamicin (antibiotic). Initially, the optimal quantities of AX, GL, and glycerol for preparing transparent, bubble-free, smooth, and foldable AX-GL films were found. Physiochemical, thermal, morphological, drug release, and antibacterial characteristics of the AX-GL films were evaluated to investigate their suitability as wound dressings. The findings suggested that the mechanical, water vapor transmission, morphological, and expansion characteristics of the optimized AX-GL films were within the required range for wound dressing. The results of Fourier-transform infrared (FTIR) analyses suggested chemical compatibility among the ingredients of the films. In in vitro drug release and antibacterial activity experiments, gentamicin (GM)-loaded AX-GL films released approximately 89% of the GM in 24 h and exhibited better antibacterial activity than standard GM solution. These results suggest that AX-GL films could serve as a promising dressing to protect against wound infections.