Prenatal cardiac anomalies, commonly referred to as congenital heart defects (CHDs), comprise a spectrum of pathologies that adversely affect cardiac function. There is a correlation between the numerous risks of cardiovascular diseases and the pressing requirement for precise, reliable, and efficient methods of early detection. The contemporary epoch of voluminous data presents a plethora of novel prospects for clinicians to utilize artificial intelligence in order to identify and enhance treatment for pediatric patients and those afflicted with congenital heart disease. Machine learning, a prevalent technique in the field of artificial intelligence, has been utilized to forecast various outcomes in obstetrics. The application of artificial intelligence in real-time electronic health recording and predictive modelling has demonstrated promising outcomes in the domain of fetal monitoring. The present research provides an in-depth review of recent advancements and challenges in the application of artificial intelligence techniques, such as deep learning and computer vision, for the detection of congenital heart disease.
Through the study of human genetic diversity, it can be predicted that complex traits, such as height and obesity, will be demonstrated. With the development of a new design technique using Surface Plasmon Resonance (SPR) for cancer cell detection and RNA single detection, the current work has been undertaken. The shape of the octagon and cross made the resonance design of the current SPR sensor work, and the sensitivity rates are distributed within a 100 nm interval of the UV region, from 2280 to 2380 nm. The output sensitivity rates for the current work show 357.14 nm/RIU achieved for the cancerous Blood (Jurkat) and 350 nm/RIU is the Skin (Basal) cancerous cell with gold and silver (Au-Ag) composition over Silicon carbide (SiC) substrate. The quality factors reached 1167.5 and 1166.5 for the two detected cancerous cells of Jurkat and Basal, respectively. The current SPR work is explored with the transmission output lines and based on the used refractive index values of the biomolecules. The sections of the proposed biosensor will present design structure, the lithography section, the analysis, and the comparison sections. With other cancer cell detection in the human body, like breast, cervical, and adrenal glands, and other biomolecules can be detected, as the applications of the current biosensor. Moreover, with the study of systems genetics, we can also explore the organism-level variations and the importance of these genetic influences in environmental diversity.
Dravidian languages, including Tamil, Telugu, Kannada, and Malayalam, have complex orthographic structures, making script identification challenging particularly for camera-based document images. This study proposes a hybrid approach that combines deep learning and texture-based methods for robust script recognition. The GoogLeNet convolutional neural network (CNN) model is used to extract deep features, while local binary patterns (LBP) and histogram of oriented gradients (HOG) capture texture characteristics. These features are fused and classified using support vector machine (SVM) classifier. Results show that CNN features alone achieve 84.50% accuracy, LBP achieves 85.90%, and HOG achieves 76.10%, while their fusion significantly improves accuracy to 92.10%. The combination of CNN and HOG features reaches 95.00% accuracy, demonstrating the effectiveness of integrating deep learning with texture-based approaches. This method has applications in OCR systems and assistive technologies for the visually impaired.