35 research outputs found
Enhanced Skin Disease Classification via Dataset Refinement and Attention-Based Vision Approach
No full textSkin diseases are listed among the most frequently encountered diseases. Skin diseases such as eczema, melanoma, and others necessitate early diagnosis to avoid further complications. This study aims to enhance the diagnosis of skin disease by utilizing advanced image processing techniques and an attention-based vision approach to support dermatologists in solving classification problems. Initially, the image is being passed through various processing steps to enhance the quality of the dataset. These steps are adaptive histogram equalization, binary cross-entropy with implicit averaging, gamma correction, and contrast stretching. Afterwards, enhanced images are passed through the attention-based approach for performing classification which is based on the encoder part of the transformers and multi-head attention. Extensive experimentation is performed to collect the various results on two publicly available datasets to show the robustness of the proposed approach. The evaluation of the proposed approach on two publicly available datasets shows competitive results as compared to a state-of-the-art approach
Hand Lines and Medical Science
No full textBackground: To assess scientific logic and common beliefs, regarding life line. Methods: In this descriptive study, one hundred critically ill patients in the surgical department and one hundred normal person as control were included . Photographs of both the hands of the patients and control groups were analyzed for life line. Results: Majority of the patients (64%) had clear life line . In control group 70% had clear life line . There was no major difference in the pattern of life line in both the groups. Conclusion: There is no scientific reason to believe that hand lines have any impact on the life or luck of a person
A systematic review of non-functional requirements mapping into architectural styles
No full textFortunately, the software attracted enough businesses to the market, allowing them to earn money in less time with less work and more accurate results. Software development life cycle (SDLC) is used for software development as it is responsible for system functionality, efficiency, maintainability, and any other non-functional system requirements. Each stage of the SDLC process is critical. However, software requirements and software architecture are both fundamental activities that play a vital role in all other SDLC stages. Non-functional requirements are critical to the success of any software because they explain all system quality attributes such as complexity, reliability, security, and maintainability, among others. The architectural styles assist you in determining which architecture may be best for your project requirements. This paper discusses several of the most important architectural styles that are best suited for mapping desired nonfunctional requirements for software development, as well as their comparison based on various quality attributes (non-functional requirements)
Diabetes insipidus: the basic and clinical review
No full textDiabetes insipidus (DI) is a complex disease. DI is inability of the body to conserve water. Polydipsia and polyuria are the major manifestations of DI. DI has various variants including central diabetes insipidus (due to defect in ADH secretion), nephrogenic diabetes insipidus (due to defect in ADH receptors or urea receptors), gestational diabetes insipidus (due to catabolism of ADH by placental vasopressinase) and primary polydipsia (due to massive fluid intake). The cause of various variants of DI is either acquired or congenital. High plasma osmolality due to hypotonic urine excretion can be fatal because it can cause psychosis, lethargy, seizures, coma or even death. Polyuria and polydipsia help in the diagnosis of DI. Differential diagnosis of various variants of DI can be carried out on the basis of water deprivation test, MRI and other radiological techniques. The proper management of DI is the replenishment of water loss and correction of clinical presentations produced as a result of DI, major is hypernatremia. The best management for primary polydipsia is fluid restriction while fluid intake is used for adipsic diabetes insipidus. ADH replacement therapy is widely used to treat DI. DDAVP or desmopressin is mostly preferred ADH analogue because it has less side effects and resistant to placental vasoprssinase
Realistic Face Super-Resolution via Generative Adversarial Networks: Enhancing Facial Recognition in Real-world Scenarios
No full texthe accuracy of real-world facial recognition operations faces challenges because of the difficulties connected to Low-Resolution image quality. This indicates that super-resolution methods play a vital role in improving recognition outcomes. Currently, available SR techniques do not achieve generalization due to their dependence on synthetic LR data that uses basic down sampling processes. The proposed GAN-based approach establishes a solution to this challenge through its simulation of actual degradation algorithms which combine Gaussian blur with noise addition and color modification and JPEG compression. Random application of augmentation parameters allows the GAN model to acquire knowledge about diverse and realistic low-resolution data distribution patterns during training. A unique unaligned face image pair dataset was made specifically for research using Zoom-In and Zoom-Out methods to capture high-resolution and low-resolution images from the same individuals. The dataset presents authentic real-life scenarios better than conventional paired collection methods. Based on experimental results our method produces substantial gains in performance compared to other super-resolution methods across both self-created face data as well as established surveillance data. The proposed model achieves higher visual quality standards while improving facial recognition accuracy under different operational situations. In conclusion, this study implements an effective SR solution for facial recognition which tackles problems with standard training datasets while creating authentic face image data. The proposed method shows promise for enhancing SR applications which need high-quality facial recognition capability in surveillance systems and other security-based operations
Realistic Face Super-Resolution via Generative Adversarial Networks: Enhancing Facial Recognition in Real-world Scenarios
No full texthe accuracy of real-world facial recognition operations faces challenges because of the difficulties connected to Low-Resolution image quality. This indicates that super-resolution methods play a vital role in improving recognition outcomes. Currently, available SR techniques do not achieve generalization due to their dependence on synthetic LR data that uses basic down sampling processes. The proposed GAN-based approach establishes a solution to this challenge through its simulation of actual degradation algorithms which combine Gaussian blur with noise addition and color modification and JPEG compression. Random application of augmentation parameters allows the GAN model to acquire knowledge about diverse and realistic low-resolution data distribution patterns during training. A unique unaligned face image pair dataset was made specifically for research using Zoom-In and Zoom-Out methods to capture high-resolution and low-resolution images from the same individuals. The dataset presents authentic real-life scenarios better than conventional paired collection methods. Based on experimental results our method produces substantial gains in performance compared to other super-resolution methods across both self-created face data as well as established surveillance data. The proposed model achieves higher visual quality standards while improving facial recognition accuracy under different operational situations. In conclusion, this study implements an effective SR solution for facial recognition which tackles problems with standard training datasets while creating authentic face image data. The proposed method shows promise for enhancing SR applications which need high-quality facial recognition capability in surveillance systems and other security-based operations
Reduction of Correlation Coefficient Using Frequency Selective Surface for Multi-band MIMO Antenna
No full text
Localization and Classification of Gastrointestinal Tract Disorders Using Explainable AI from Endoscopic Images
No full textGlobally, gastrointestinal (GI) tract diseases are on the rise. If left untreated, people may die from these diseases. Early discovery and categorization of these diseases can reduce the severity of the disease and save lives. Automated procedures are necessary, since manual detection and categorization are laborious, time-consuming, and prone to mistakes. In this work, we present an automated system for the localization and classification of GI diseases from endoscopic images with the help of an encoder–decoder-based model, XceptionNet, and explainable artificial intelligence (AI). Data augmentation is performed at the preprocessing stage, followed by segmentation using an encoder–decoder-based model. Later, contours are drawn around the diseased area based on segmented regions. Finally, classification is performed on segmented images by well-known classifiers, and results are generated for various train-to-test ratios for performance analysis. For segmentation, the proposed model achieved 82.08% dice, 90.30% mIOU, 94.35% precision, and 85.97% recall rate. The best performing classifier achieved 98.32% accuracy, 96.13% recall, and 99.68% precision using the softmax classifier. Comparison with the state-of-the-art techniques shows that the proposed model performed well on all the reported performance metrics. We explain this improvement in performance by utilizing heat maps with and without the proposed technique
