Search

Melanoma is dangerous skin cancer disease with high malignancy potential, necessitates advanced detection methods for improved patient outcomes. This study proposes a novel factor-aware, edge computing-based framework, leveraging a customized VGG16 architecture. The framework prioritizes real-time analysis and privacy preservation, acknowledging the diverse risk factors influencing melanoma development. This work has led to the development of a factor-aware approach, a customized VGG16 architecture for the classification of melanoma, and an edge device privacy-centric system. Tests contrasting traditional and customized VGG16 architectures demonstrate the enhanced effectiveness of the customized architecture, attaining a balanced categorization of both benign and malignant instances. The proposed system works well for processing skin lesion images at the data source, cutting down on latency and protecting patient privacy. Experiments conducted in comparison with traditional VGG16 architecture show increased F1-scores, recall, and precision in the classification of benign and malignant cases. The customized VGG16 architecture achieves an accuracy boost from 0.84 to 0.88, outperforming the competition consistently. Confusion matrices show a decrease in false positives and negatives, which suggests improved diagnostic precision. Improved discriminative power is demonstrated by the Receiver Operating Characteristic (ROC) curves, which indicate a higher area under the curve (AUC) for the customized VGG16 architecture (0.95). In comparison to traditional architecture (AP =0.58), precision-recall curves show a higher Average Precision (AP) score of 0.94, demonstrating a stronger balance between recall and precision. The proposed framework offers measurable gains in the accuracy of melanoma diagnosis in addition to introducing novel approaches. These findings highlight the possibility of transforming early detection and treatment, which would eventually enhance patient outcomes and the provision of healthcare for the management of melanoma.

Melanoma, a global health concern, undergoes a transformative shift in early diagnosis through the integration of artificial intelligence (AI) and environmental factors. Exposure to UVB is the main cause of DNA deterioration in skin cells. The DNA molecules absorb UVB photons, which causes the creation of photoproducts such as pyrimidine (6-4), pyrimidone photoproducts (6-4PPS), and cyclobutane pyrimidine dimers (CPDs). These photoproducts alter important genes, including those that control cell development and apoptosis. These genetic changes accumulate over time as a result of UV-induced DNA damage to melanocytes, turning normal cells into malignant melanoma cells. This study explores the incorporation of ultraviolet (UV) radiation, DNA damage, UV signature mutations, skin pigmentation, melanin biochemistry, and gene-environment interactions into AI-powered melanoma identification systems. The analysis highlights the importance of these factors, contributing to the intricacies of melanoma and emphasizing their critical inclusion in predictive models. Design goals for AI systems prioritize accuracy, customization, comprehensibility, and ethical adherence. AI emerges as a potent ally in reshaping public health initiatives, identifying high-risk areas and populations, redefining early detection, and preventing melanoma on a population-wide scale. The increased incidence of melanoma cases globally can be attributed to overexposure to ultraviolet (UV) radiation. As a significant risk component, this environmental factor is responsible for the startling increase in melanoma incidence that has been occurring since the mid-1960s. The digital dermoscopy in conjunction with AI and environmental factors has demonstrated potential to support early melanoma detection. This study underscores the potential of AI to revolutionize melanoma research, leveraging insights from UV radiation, DNA damage, UV signature mutations, skin pigmentation, melanin biochemistry, and their interactions for enhanced diagnostic capabilities and improved public health outcomes.

Recent advancements in image processing and computer vision have brought significant transformations in healthcare technology, leading to significant improvements in diagnosis accuracy, cost-effectiveness, and time efficiency. Magnetic Resonance Imaging (MRI) is employed by the radiologist for its remarkable ability to detect even the most subtle brain abnormalities. This study considers a comprehensive analysis of the two prominent object identification frameworks, YOLOv5 and YOLOv7, leveraging state-of-the-art deep learning architectures to classify and detect brain cancers within MRI. The brain tumor dataset encompasses three distinct classes, including meningiomas, gliomas and pituitary tumors. To ensure precise segmentation of the tumor regions, the preprocessing phase incorporates advanced mask alignment techniques. This preprocessed dataset has been used to evaluate the performance of the deep learning models for brain tumor detection and classification. From the numerical results of YOLOv5, it was noticed that a recall score of 0.905 for box detection and 0.906 for mask segmentation, with a precision score of 0.94 and 0.936, respectively. At an IoU threshold of 0.5, both box detection and mask segmentation achieve a mAP of 0.947, whereas, at an IoU threshold of 0.5 to 0.95, they achieve mAPs of 0.666 and 0.657, respectively. In comparison, YOLOv7 exhibits strong performance with box detection accuracy of 0.936 and a mask segmentation accuracy of 0.935. The recall score are 0.904 for box detection and mask segmentation is 0.903. Notably, the mAP result at the IoU threshold of 0.5 are 0.94 for box detection and mask segmentation is 0.941. Over the broader IoU spectrum of 0.5 to 0.95, the mAP was 0.677 for box detection and 0.659 for mask segmentation. To underscore the novelty of the approach, the performance of the proposed framework is systematically compared with established methods such as RCNN, Faster RCNN, and Mask RCNN.

Breast cancer continues to pose a substantial worldwide public health concern, necessitating the use of sophisticated diagnostic methods to enable timely identification and management. The present research utilizes an iterative methodology for collaborative learning, using Deep Neural Networks (DNN) to construct a breast cancer detection model with a high level of accuracy. By leveraging Federated Learning (FL), this collaborative framework effectively utilizes the combined knowledge and data assets of several healthcare organizations while ensuring the protection of patient privacy and data security. The model described in this study showcases significant progress in the field of breast cancer diagnoses, with a maximum accuracy rate of 97.54%, precision of 96.5%, and recall of 98.0%, by using an optimum feature selection technique. Data augmentation approaches play a crucial role in decreasing loss and improving model performance. Significantly, the F1-Score, a comprehensive metric for evaluating performance, turns out to be 97%. This study signifies a notable advancement in the field of breast cancer screening, fostering hope for improved patient outcomes via increased accuracy and reliability. This study highlights the potential impact of collaborative learning, namely, in the field of FL, in transforming breast cancer detection. The incorporation of privacy considerations and the use of diverse data sources contribute to the advancement of early detection and the treatment of breast cancer, hence yielding significant benefits for patients on a global scale.

Sumoylation is a post-translation modification (PTM) mechanism that involves many critical biological processes, such as gene expression, localizing and stabilizing proteins, and replicating the genome. Moreover, sumoylation sites are associated with different diseases, including Parkinson’s and Alzheimer’s. Due to its vital role in the biological process, identifying sumoylation sites in proteins is significant for monitoring protein functions and discovering multiple diseases. Therefore, in the literature, several computational models utilizing conventional ML methods have been introduced to classify sumoylation sites. However, these models cannot accurately classify the sumoylation sites due to intrinsic limitations associated with the conventional learning methods. This paper proposes a robust computational model (called Deep-Sumo) for predicting sumoylation sites based on a deep-learning algorithm with efficient feature representation methods. The proposed model employs a half-sphere exposure method to represent protein sequences in a feature vector. Principal Component Analysis is applied to extract discriminative features by eliminating noisy and redundant features. The discriminant features are given to a multilayer Deep Neural Network (DNN) model to predict sumoylation sites accurately. The performance of the proposed model is extensively evaluated using a 10-fold cross-validation test by considering various statistical-based performance measurement metrics. Initially, the proposed DNN is compared with the traditional learning algorithm, and subsequently, the performance of the Deep-Sumo is compared with the existing models. The validation results show that the proposed model reports an average accuracy of 96.47%, with improvement compared with the existing models. It is anticipated that the proposed model can be used as an effective tool for drug discovery and the diagnosis of multiple diseases.

Alzheimer’s disease is a common neurological disorder and mental disability that causes memory loss and cognitive decline, presenting a major challenge to public health due to its impact on millions of individuals worldwide. It is crucial to diagnose and treat Alzheimer’s in a timely manner to improve the quality of life of both patients and caregivers. In the recent past, machine learning techniques have showed potential in detecting Alzheimer’s disease by examining neuroimaging data, especially Magnetic Resonance Imaging (MRI). This research proposes an attention-based mechanism that employs the vision transformer approach to detect Alzheimer’s using MRI images. The presented technique applies preprocessing to the MRI images and forwards them to a vision transformer network for classification. This network is trained on the publicly available Kaggle dataset, and it illustrated impressive results with an accuracy of 99.06%, precision of 99.06%, recall of 99.14%, and F1-score of 99.1%. Furthermore, a comparative study is also conducted to evaluate the performance of the proposed method against various state-of-the-art techniques on diverse datasets. The proposed method demonstrated superior performance, outperforming other published methods when applied to the Kaggle dataset.

Motor imagery, an intricate cognitive procedure encompassing the mental simulation of motor actions, has surfaced as a potent strategy within the neuro-rehabilitation domain. It presents a non-invasive, economically viable method for facilitating individuals with disabilities in enhancing their motor functionality and regaining self-sufficiency. This manuscript delivers an exhaustive analysis of the significance of motor imagery in augmenting functional rehabilitation for individuals afflicted with physical impairments. It investigates the fundamental mechanisms governing motor imagery, its applications across diverse disability conditions, and the prospective advantages it renders. Moreover, this document addresses the prevailing obstacles and prospective trajectories in this sector, accentuating the necessity for continued investigation and the invention of cutting-edge technologies that optimize the potentiality of motor imagery in aiding disabled persons.

Healthcare is a critical field of research and equally important for all nations. Providing secure healthcare facilities to citizens is the primary concern of each nation. However, people living in remote areas do not get timely and sufficient healthcare facilities, even in developed countries. During the recent COVID-19 pandemic, many fatalities occurred due to the inaccessibility of healthcare facilities on time. Therefore, there is a need to propose a solution that may help citizens living in remote areas with proper and secure healthcare facilities without moving to other places. The revolution in ICT technologies, especially IoT, 5G, and cloud computing, has made access to healthcare facilities easy and approachable. There is a need to benefit from these technologies so that everyone can get secure healthcare facilities from anywhere. This research proposes a framework that will ensure 24/7 accessibility of healthcare facilities by anyone from anywhere, especially in rural areas with fewer healthcare facilities. In the proposed approach, the patients will receive doorstep treatment from the remote doctor in rural areas or the nearby local clinic. Healthcare resources (doctor, treatment, patient counseling, diagnosis, etc.) will be shared remotely with people far from these facilities. The proposed approach is tested using mathematical modeling and a case study, and the findings confirm that the proposed approach helps improve healthcare facilities for remote patients.

Monkeypox (MPX) is a disease caused by monkeypox virus (MPXV). It is a contagious disease and has associated symptoms of skin lesions, rashes, fever, and respiratory distress lymph swelling along with numerous neurological distresses. This can be a deadly disease, and the latest outbreak of it has shown its spread to Europe, Australia, the United States, and Africa. Typically, diagnosis of MPX is performed through PCR, by taking a sample of the skin lesion. This procedure is risky for medical staff, as during sample collection, transmission and testing, they can be exposed to MPXV, and this infectious disease can be transferred to medical staff. In the current era, cutting-edge technologies such as IoT and artificial intelligence (AI) have made the diagnostics process smart and secure. IoT devices such as wearables and sensors permit seamless data collection while AI techniques utilize the data in disease diagnosis. Keeping in view the importance of these cutting-edge technologies, this paper presents a non-invasive, non-contact, computer-vision-based method for diagnosis of MPX by analyzing skin lesion images that are more smart and secure compared to traditional methods of diagnosis. The proposed methodology employs deep learning techniques to classify skin lesions as MPXV positive or not. Two datasets, the Kaggle Monkeypox Skin Lesion Dataset (MSLD) and the Monkeypox Skin Image Dataset (MSID), are used for evaluating the proposed methodology. The results on multiple deep learning models were evaluated using sensitivity, specificity and balanced accuracy. The proposed method has yielded highly promising results, demonstrating its potential for wide-scale deployment in detecting monkeypox. This smart and cost-effective solution can be effectively utilized in underprivileged areas where laboratory infrastructure may be lacking.

The expansion of technology in metropolitan centers draws people to cities, which causes excessive traffic on the roadways during peak hours. This exacerbated the traffic situation, resulting in a delay, a loss of resources, and a waste of time. Like any other metropolitan metropolis, Riyadh, Saudi Arabia, has everyday traffic congestion during business hours. The current traffic management has made many attempts to ease traffic congestion in cities; despite these measures, the problem has not been solved adequately. To handle this road congestion, there is a need to appropriately store the big data collected by traffic sensors and utilize it for efficient traffic management employing cutting-edge technology. This study provides an architecture for a smart traffic management system that uses modern technologies such as the Internet of Things (IoT), cloud computing, 5G, and big data to aid conventional traffic management systems and efficiently handle the stated problem. The proposed technique has the potential to reduce traffic congestion significantly. Our proposed solution encourages mobility by using roadside messaging agents to offer real-time traffic information on traffic congestion and unexpected traffic incidents. Citizens will save time by getting these early warning messages, particularly during peak hours. As part of the suggested method, each signal dashboard gets traffic information. A case study is used in the research to evaluate alternative solutions to traffic congestion. The case study results show that the proposed strategy outperforms the present options.

Security and performance (SAP) are two critical NFRs that affect the successful completion of software projects. Organizations need to follow the practices that are vital to SAP verification. These practices must be incorporated into the software development process to identify SAP-related defects and avoid failures after deployment. This can only be achieved if organizations are fully aware of SAP verification activities and appropriately include them in the software development process. However, there is a lack of awareness of the factors that influence SAP verification, which makes it difficult for businesses to improve their verification efforts and ensure that the released software meets these requirements. To fill this gap, this research study aimed to identify the mediating factors (MFs) influencing SAP verification and the actions to promote them. Ten MFs and their corresponding actions were identified after thoroughly reviewing the existing literature. The mapping of MFs and their corresponding actions were initially evaluated with the help of a pilot study. Mathematical modeling was utilized to model these MFs and examine each MF’s unique effect on software SAP verification. In addition, two case studies with a small- and a medium-sized organization were used to better understand the function these MFs play in the process of SAP verification. The research findings suggested that MFs assist software development organizations in their efforts to integrate SAP verification procedures into their standard software systems. Further investigation is required to support the understanding of these MFs when building modern software systems.

A robust facial recognition system that has soundness and completeness is essential for authorized control access to lawful resources. Due to the availability of modern image manipulation technology, the current facial recognition systems are vulnerable to different biometric attacks. Image morphing attack is one of these attacks. This paper compares and analyzes state-of-the-art morphing attack detection (MAD) methods. The performance of different MAD methods is also compared on a wide range of source image databases. Moreover, it also describes the morph image generation techniques along with the limitations, strengths, and drawbacks of each morphing technique. Results are investigated and compared with in-depth analysis providing insight into the vulnerabilities of existing systems. This paper provides vital information that is essential for building a next generation morph attack detection system.