Search

Lung sounds contribute essential information about a patient's health. Here, for detecting adventitious sounds of lungs, two sets of eight features each (total 16 features), based on wavelet bi-spectrum (WBS) and power spectrum (WPS), respectively, are proposed. The feature sets are analyzed using five classifiers with one to seven sub-classifier types. A matrix (17X14) of seven evaluation parameters compares the feature sets. Results show that Random Forest, Random Tree, Random committee with WPS and WBS features, LMT with WPS, and Randomizable filter classifier with WBS have shown the best results updating the accuracy obtained in previous researches. [ABSTRACT FROM AUTHOR]

An efficient deep learning framework for spine abnormalities is the focus of this study, which is devoted to its investigation. The process of diagnosing back pain with the currently available methods may be time-consuming, laborious, and very subjective. When many physicians work on the same graduation thesis, the grades may be different since each doctor comes from a unique background and has a unique set of talents. These notable differences are compounded by the differences in clinical outcomes observed by the physicians involved, i.e. the evaluations made by spine surgeons when analyzing pathologies of the lumbar spine may differ from those made by orthopedic surgeons. This is because spine surgeons specialize in the lumbar spine. As can be shown, the suggested technique and the physician's evaluation of ALL (MAE 1.44°) had a correlation coefficient of 0.968. An improvement of 0.78 percent is achieved using the suggested framework in comparison to the previous system (in R). Although this is an indirect comparison, physicians have significant differences in how they evaluate various treatment alternatives. The R and MAE ratings provide evidence that the spinal measurements acquired via the use of the suggested methodology had a strong correlation with the findings of experienced doctors, which was statistically significant (i.e., p less than 0.05). [ABSTRACT FROM AUTHOR]

The present paper is related to the survey on the Investigation on Efficient Deep Learning Framework for Sipal Deformities. In this paper, some selected papers are taken for the investigation to find research gaps or extensions of existing research in the selected domain. The central nervous system is the most significant processing unit in the human body, and it is located in the central nervous system. Management and control of all the key organs from head to toe including eye blinking, breathing, heart pumping and movement of motion including bending and twisting are all managed and controlled by this system. The central nervous system is comprised of two primary organs: the brain, which is the most important, and the spinal cord, which is the second most important. The brain stem serves as the spinal column's beginning point. In its most basic form, the spinal cord is a delicate vertical pipe with a solid texture that includes a collection of nerves and tissues. [ABSTRACT FROM AUTHOR]

Accurately identifying all objects of interest inside the specified frame of reference is crucial for object identification techniques to allow machine vision to interpret images successfully. Theoretical frameworks from computer vision and deep learning have informed many potential solutions to this problem. However, current approaches frequently fail when faced with objects going through random geometric changes and continually show shortcomings when identifying small, dense objects. This research looks at state-of-the-art object detection methods, compares them, and then suggests a convolutional object detection network that has been tweaked to fix the problems with the existing methods. Comparing our research to existing approaches, we find that they perform better. We accomplish this by training deep convolutional networks to detect geometric transformations and adjusting the networks to handle multi-scaled features. The results achieved after the optimization of the You only look once (YOLO) V5 & V7 are stated in this paper. The experiments demonstrated that YOLO v8 achieved higher accuracy than the hyper-tuned YOLO V5 and V7, with an average Precision (mAP) score of 52.8% on the customized military dataset running at 60 Frames Per Second (FPS). Object detection using deep neural networks (DNNs) poses a significant challenge due to the high computational and power requirements, mainly when deployed on general-purpose platforms such as CPUs and GPUs. However, addressing these limitations becomes crucial for efficient edge computing tasks like object detection, where faster, smaller, and energy-efficient solutions are essential. To overcome these challenges, system-on-chip (SoC) designs emerge as a promising solution. [ABSTRACT FROM AUTHOR]