Search Results (48)

Skin cancer is a class of disorder defined by the growth of abnormal cells on the body. Accurately identifying and diagnosing skin lesions is quite difficult because skin malignancies share many common characteristics and a wide range of morphologies. To face this challenge, deep learning algorithms have been proposed. Deep learning algorithms have shown diagnostic efficacy comparable to dermatologists in the discipline of images-based skin lesion diagnosis in recent research articles. This work proposes a novel deep learning algorithm to detect skin cancer. The proposed CAD-Skin system detects and classifies skin lesions using deep convolutional neural networks and autoencoders to improve the classification efficiency of skin cancer. The CAD-Skin system was designed and developed by the use of the modern preprocessing approach, which is a combination of multi-scale retinex, gamma correction, unsharp masking, and contrast-limited adaptive histogram equalization. In this work, we have implemented a data augmentation strategy to deal with unbalanced datasets. This step improves the model’s resilience to different pigmented skin conditions and avoids overfitting. Additionally, a Quantum Support Vector Machine (QSVM) algorithm is integrated for final-stage classification. Our proposed CAD-Skin enhances category recognition for different skin disease severities, including actinic keratosis, malignant melanoma, and other skin cancers. The proposed system was tested using the PAD-UFES-20-Modified, ISIC-2018, and ISIC-2019 datasets. The system reached accuracy rates of 98%, 99%, and 99%, consecutively, which is higher than state-of-the-art work in the literature. The minimum accuracy achieved for certain skin disorder diseases reached 97.43%. Our research study demonstrates that the proposed CAD-Skin provides precise diagnosis and timely detection of skin abnormalities, diversifying options for doctors and enhancing patient satisfaction during medical practice. Full article

The early prediction of ocular disease is certainly an obligatory concern in the domain of ophthalmic medicine. Although modern scientific discoveries have shown the potential to treat eye diseases by using artificial intelligence (AI) and machine learning, explainable AI remains a crucial challenge confronting this area of research. Although some traditional methods put in significant effort, they cannot accurately predict the proper ocular diseases. However, incorporating AI into diagnosing eye diseases in healthcare complicates the situation as the decision-making process of AI demonstrates complexity, which is a significant concern, especially in major sectors like ocular disease prediction. The lack of transparency in the AI models may hinder the confidence and trust of the doctors and the patients, as well as their perception of the AI and its abilities. Accordingly, explainable AI is significant in ensuring trust in the technology, enhancing clinical decision-making ability, and deploying ocular disease detection. This research proposed an efficient transfer learning model for eye disease prediction to transform smart vision potential in the healthcare sector and meet conventional approaches’ challenges while integrating explainable artificial intelligence (XAI). The integration of XAI in the proposed model ensures the transparency of the decision-making process through the comprehensive provision of rationale. This proposed model provides promising results with 95.74% accuracy and explains the transformative potential of XAI in advancing ocular healthcare. This significant milestone underscores the effectiveness of the proposed model in accurately determining various types of ocular disease. It is clearly shown that the proposed model is performing better than the previously published methods. Full article

Tribolium castaneum (Herbst) (Coleoptera: Tenebrionidae) is the most destructive pest of stored grain commodities. To control the attack of this insect pest, it is important to develop non-hazardous alternatives to replace fumigants. This study examined the fumigant toxicity and repellent activity of seven essential oils (Chinopodium ambrosiodes, Pinus roxburghii, Zanthoxylum armatum, Lepidium sativum, Azadirachta indica, Baccharis teindalensis, and Origanum majorana) against adult T. castaneum under controlled laboratory conditions. The fumigant toxicity and repellent activities of essential oils were tested using five different doses (62.5, 125, 250, 500, and 1000 µg) in vapour-phase fumigation and four-arm olfactometer bioassays, respectively. In vapor-phase fumigation bioassays, mortality data were recorded after 24, 48, and 72 h. The results showed that C. ambrosiodes and P. roxburghii essential oils are potential fumigants against adult T. castaneum. In repellency bioassays, a one-week-old adult population of T. castaneum was used to test the repellency potential of the essential oils. The results indicated that C. ambrosiodes and P. roxburghii had significant repellency potential against T. castaneum. Overall, we conclude that these essential oils have strong repellent and fumigant properties and can be used as potential repellent compounds to deter the insects. Full article

The ultra-wideband polarization converters have been of interest to researcher due to their demand in satellite communication and navigation systems. This paper presents an ultra-wideband reflective cross-polarization converter comprising a stair-shaped metasurface. By observation, the alleged structure allows the conversion of linearly polarized waves to orthogonal components, having a polarization conversion ratio of greater than 90% spread across the large frequency range of 12.94 to 16.54 GHz and 17.54 to 26 GHz. A highly efficient, ultra-high frequency polarization conversion is achieved by the utilization of strong electromagnetic resonance coupling between the upper and lower layers of the metasurface. Further, it is depicted that the polarization converter has a wide obliquity of incidence wave. Moreover, the simulation and measured results show a good match. The linear polarization converter is simple in design but is of high performance, and therefore, might be useful in satellite communication, imaging systems, and navigation systems. Full article

Biometric authentication is a widely used method for verifying individuals’ identities using photoplethysmography (PPG) cardiac signals. The PPG signal is a non-invasive optical technique that measures the heart rate, which can vary from person to person. However, these signals can also be changed due to factors like stress, physical activity, illness, or medication. Ensuring the system can accurately identify and authenticate the user despite these variations is a significant challenge. To address these issues, the PPG signals were preprocessed and transformed into a 2-D image that visually represents the time-varying frequency content of multiple PPG signals from the same human using the scalogram technique. Afterward, the features fusion approach is developed by combining features from the hybrid convolution vision transformer (CVT) and convolutional mixer (ConvMixer), known as the CVT-ConvMixer classifier, and employing attention mechanisms for the classification of human identity. This hybrid model has the potential to provide more accurate and reliable authentication results in real-world scenarios. The sensitivity (SE), specificity (SP), F1-score, and area under the receiver operating curve (AUC) metrics are utilized to assess the model’s performance in accurately distinguishing genuine individuals. The results of extensive experiments on the three PPG datasets were calculated, and the proposed method achieved ACCs of 95%, SEs of 97%, SPs of 95%, and an AUC of 0.96, which indicate the effectiveness of the CVT-ConvMixer system. These results suggest that the proposed method performs well in accurately classifying or identifying patterns within the PPG signals to perform continuous human authentication. Full article

The primary objective of this study is to develop an advanced, automated system for the early detection and classification of leaf diseases in potato plants, which are among the most cultivated vegetable crops worldwide. These diseases, notably early and late blight caused by Alternaria solani and Phytophthora infestans, significantly impact the quantity and quality of global potato production. We hypothesize that the integration of Vision Transformer (ViT) and ResNet-50 architectures in a new model, named EfficientRMT-Net, can effectively and accurately identify various potato leaf diseases. This approach aims to overcome the limitations of traditional methods, which are often labor-intensive, time-consuming, and prone to inaccuracies due to the unpredictability of disease presentation. EfficientRMT-Net leverages the CNN model for distinct feature extraction and employs depth-wise convolution (DWC) to reduce computational demands. A stage block structure is also incorporated to improve scalability and sensitive area detection, enhancing transferability across different datasets. The classification tasks are performed using a global average pooling layer and a fully connected layer. The model was trained, validated, and tested on custom datasets specifically curated for potato leaf disease detection. EfficientRMT-Net’s performance was compared with other deep learning and transfer learning techniques to establish its efficacy. Preliminary results show that EfficientRMT-Net achieves an accuracy of 97.65% on a general image dataset and 99.12% on a specialized Potato leaf image dataset, outperforming existing methods. The model demonstrates a high level of proficiency in correctly classifying and identifying potato leaf diseases, even in cases of distorted samples. The EfficientRMT-Net model provides an efficient and accurate solution for classifying potato plant leaf diseases, potentially enabling farmers to enhance crop yield while optimizing resource utilization. This study confirms our hypothesis, showcasing the effectiveness of combining ViT and ResNet-50 architectures in addressing complex agricultural challenges. Full article

In the current digital era, Wireless Sensor Networks (WSNs) and the Internet of Things (IoT) are evolving, transforming human experiences by creating an interconnected environment. However, ensuring the security of WSN-IoT networks remains a significant hurdle, as existing security models are plagued with issues like prolonged training durations and complex classification processes. In this study, a robust cyber-physical system based on the Emphatic Farmland Fertility Integrated Deep Perceptron Network (EFDPN) is proposed to enhance the security of WSN-IoT. This initiative introduces the Farmland Fertility Feature Selection (F³S) technique to alleviate the computational complexity of identifying and classifying attacks. Additionally, this research leverages the Deep Perceptron Network (DPN) classification algorithm for accurate intrusion classification, achieving impressive performance metrics. In the classification phase, the Tunicate Swarm Optimization (TSO) model is employed to improve the sigmoid transformation function, thereby enhancing prediction accuracy. This study demonstrates the development of an EFDPN-based system designed to safeguard WSN-IoT networks. It showcases how the DPN classification technique, in conjunction with the TSO model, significantly improves classification performance. In this research, we employed well-known cyber-attack datasets to validate its effectiveness, revealing its superiority over traditional intrusion detection methods, particularly in achieving higher F1-score values. The incorporation of the F3S algorithm plays a pivotal role in this framework by eliminating irrelevant features, leading to enhanced prediction accuracy for the classifier, marking a substantial stride in fortifying WSN-IoT network security. This research presents a promising approach to enhancing the security and resilience of interconnected cyber-physical systems in the evolving landscape of WSN-IoT networks. Full article

Hypertensive retinopathy (HR) and diabetic retinopathy (DR) are retinal diseases closely associated with high blood pressure. The severity and duration of hypertension directly impact the prevalence of HR. The early identification and assessment of HR are crucial to preventing blindness. Currently, limited computer-aided methods are available for detecting HR and DR. These existing systems rely on traditional machine learning approaches, which require complex image processing techniques and are often limited in their application. To address this challenge, this work introduces a deep learning (DL) method called HDR-EfficientNet, which aims to provide an efficient and accurate approach to identifying various eye-related disorders, including diabetes and hypertensive retinopathy. The proposed method utilizes an EfficientNet-V2 network for end-to-end training focused on disease classification. Additionally, a spatial-channel attention method is incorporated into the approach to enhance its ability to identify specific areas of damage and differentiate between different illnesses. The HDR-EfficientNet model is developed using transfer learning, which helps overcome the challenge of imbalanced sample classes and improves the network’s generalization. Dense layers are added to the model structure to enhance the feature selection capacity. The performance of the implemented system is evaluated using a large dataset of over 36,000 augmented retinal fundus images. The results demonstrate promising accuracy, with an average area under the curve (AUC) of 0.98, a specificity (SP) of 96%, an accuracy (ACC) of 98%, and a sensitivity (SE) of 95%. These findings indicate the effectiveness of the suggested HDR-EfficientNet classifier in diagnosing HR and DR. In summary, the HDR-EfficientNet method presents a DL-based approach that offers improved accuracy and efficiency for the detection and classification of HR and DR, providing valuable support in diagnosing and managing these eye-related conditions. Full article

Developing a simple and efficient attack detection system for ensuring the security of cloud systems against cyberthreats is a crucial and demanding process in the present time. In traditional work, various machine-learning-based detection methodologies have been developed for securing the cloud network. However, those methodologies face the complications of overfitting, complex system design, difficulty understanding, and higher time consumption. Hence, the proposed work contributes to the design and development of an effective security model for detecting cyberthreats from cloud systems. The proposed framework encompasses the modules of preprocessing and normalization, feature extraction, optimization, and prediction. An improved principal component analysis (IPCA) model is used to extract the relevant features from the normalized dataset. Then, a hybrid grasshopper–crow search optimization (GSCSO) is employed to choose the relevant features for training and testing operations. Finally, an isolated heuristic neural network (IHNN) algorithm is used to predict whether the data flow is normal or intrusive. Popular and publicly available datasets such as NSL-KDD, BoT-IoT, KDD Cup’99, and CICIDS 2017 are used for implementing the detection system. For validation, the different performance indicators, such as detection accuracy (AC) and F1-score, are measured and compared with the proposed GSCSO-IHNN system. On average, the GSCO-IHNN system achieved 99.5% ACC and 0.999 F1 scores on these datasets. The results of the performance study show that the GSCSO-IHNN method outperforms the other security models. Ultimately, this research strives to contribute to the ongoing efforts to fortify the security of cloud systems, making them resilient against cyber threats more simply and efficiently. Full article

Cloud organizations now face a challenge in managing the enormous volume of data and various resources in the cloud due to the rapid growth of the virtualized environment with many service users, ranging from small business owners to large corporations. The performance of cloud computing may suffer from ineffective resource management. As a result, resources must be distributed fairly among various stakeholders without sacrificing the organization’s profitability or the satisfaction of its customers. A customer’s request cannot be put on hold indefinitely just because the necessary resources are not available on the board. Therefore, a novel cloud resource allocation model incorporating security management is developed in this paper. Here, the Deep Linear Transition Network (DLTN) mechanism is developed for effectively allocating resources to cloud systems. Then, an Adaptive Mongoose Optimization Algorithm (AMOA) is deployed to compute the beamforming solution for reward prediction, which supports the process of resource allocation. Moreover, the Logic Overhead Security Protocol (LOSP) is implemented to ensure secured resource management in the cloud system, where Burrows–Abadi–Needham (BAN) logic is used to predict the agreement logic. During the results analysis, the performance of the proposed DLTN-LOSP model is validated and compared using different metrics such as makespan, processing time, and utilization rate. For system validation and testing, 100 to 500 resources are used in this study, and the results achieved a make-up of 2.3% and a utilization rate of 13 percent. Moreover, the obtained results confirm the superiority of the proposed framework, with better performance outcomes. Full article

The lungs are critical components of the respiratory system because they allow for the exchange of oxygen and carbon dioxide within our bodies. However, a variety of conditions can affect the lungs, resulting in serious health consequences. Lung disease treatment aims to control its severity, which is usually irrevocable. The fundamental objective of this endeavor is to build a consistent and automated approach for establishing the intensity of lung illness. This paper describes MixNet-LD, a unique automated approach aimed at identifying and categorizing the severity of lung illnesses using an upgraded pre-trained MixNet model. One of the first steps in developing the MixNet-LD system was to build a pre-processing strategy that uses Grad-Cam to decrease noise, highlight irregularities, and eventually improve the classification performance of lung illnesses. Data augmentation strategies were used to rectify the dataset’s unbalanced distribution of classes and prevent overfitting. Furthermore, dense blocks were used to improve classification outcomes across the four severity categories of lung disorders. In practice, the MixNet-LD model achieves cutting-edge performance while maintaining model size and manageable complexity. The proposed approach was tested using a variety of datasets gathered from credible internet sources as well as a novel private dataset known as Pak-Lungs. A pre-trained model was used on the dataset to obtain important characteristics from lung disease images. The pictures were then categorized into categories such as normal, COVID-19, pneumonia, tuberculosis, and lung cancer using a linear layer of the SVM classifier with a linear activation function. The MixNet-LD system underwent testing in four distinct tests and achieved a remarkable accuracy of 98.5% on the difficult lung disease dataset. The acquired findings and comparisons demonstrate the MixNet-LD system’s improved performance and learning capabilities. These findings show that the proposed approach may effectively increase the accuracy of classification models in medicinal image investigations. This research helps to develop new strategies for effective medical image processing in clinical settings. Full article

It is difficult for clinicians or less-experienced ophthalmologists to detect early eye-related diseases. By hand, eye disease diagnosis is labor-intensive, prone to mistakes, and challenging because of the variety of ocular diseases such as glaucoma (GA), diabetic retinopathy (DR), cataract (CT), and normal eye-related diseases (NL). An automated ocular disease detection system with computer-aided diagnosis (CAD) tools is required to recognize eye-related diseases. Nowadays, deep learning (DL) algorithms enhance the classification results of retinograph images. To address these issues, we developed an intelligent detection system based on retinal fundus images. To create this system, we used ODIR and RFMiD datasets, which included various retinographics of distinct classes of the fundus, using cutting-edge image classification algorithms like ensemble-based transfer learning. In this paper, we suggest a three-step hybrid ensemble model that combines a classifier, a feature extractor, and a feature selector. The original image features are first extracted using a pre-trained AlexNet model with an enhanced structure. The improved AlexNet (iAlexNet) architecture with attention and dense layers offers enhanced feature extraction, task adaptability, interpretability, and potential accuracy benefits compared to other transfer learning architectures, making it particularly suited for tasks like retinograph classification. The extracted features are then selected using the ReliefF method, and then the most crucial elements are chosen to minimize the feature dimension. Finally, an XgBoost classifier offers classification outcomes based on the desired features. These classifications represent different ocular illnesses. We utilized data augmentation techniques to control class imbalance issues. The deep-ocular model, based mainly on the AlexNet-ReliefF-XgBoost model, achieves an accuracy of 95.13%. The results indicate the proposed ensemble model can assist dermatologists in making early decisions for the diagnosing and screening of eye-related diseases. Full article

In the contemporary digital landscape, web search functions as a pivotal conduit for information dissemination. Nevertheless, blind users (BUs) encounter substantial barriers in leveraging online services, attributable to intrinsic deficiencies in the information structure presented by online platforms. A critical analysis reveals that a considerable segment of BUs perceive online service access as either challenging or unfeasible, with only a fraction of search endeavors culminating successfully. This predicament stems largely from the linear nature of information interaction necessitated for BUs, a process that mandates sequential content relevancy assessment, consequently imposing cognitive strain and fostering information disorientation. Moreover, the prevailing evaluative metrics for web service efficacy—precision and recall—exhibit a glaring oversight of the nuanced behavioral and usability facets pertinent to BUs during search engine design. Addressing this, our study introduces an innovative framework to facilitate information exploration, grounded in the cognitive principles governing BUs. This framework, piloted using the Wikipedia dataset, seeks to revolutionize the search result space through categorical organization, thereby enhancing accessibility for BUs. Empirical and usability assessments, conducted on a cohort of legally blind individuals (N = 25), underscore the framework’s potential, demonstrating notable improvements in web content accessibility and system usability, with categorical accuracy standing at 84% and a usability quotient of 72.5%. This research thus holds significant promise for redefining web search paradigms to foster inclusivity and optimized user experiences for BUs. Full article

A well-known eye disorder called diabetic retinopathy (DR) is linked to elevated blood glucose levels. Cotton wool spots, confined veins in the cranial nerve, AV nicking, and hemorrhages in the optic disc are some of its symptoms, which often appear later. Serious side effects of DR might include vision loss, damage to the visual nerves, and obstruction of the retinal arteries. Researchers have devised an automated method utilizing AI and deep learning models to enable the early diagnosis of this illness. This research gathered digital fundus images from renowned Pakistani eye hospitals to generate a new “DR-Insight” dataset and known online sources. A novel methodology named the residual-dense system (RDS-DR) was then devised to assess diabetic retinopathy. To develop this model, we have integrated residual and dense blocks, along with a transition layer, into a deep neural network. The RDS-DR system is trained on the collected dataset of 9860 fundus images. The RDS-DR categorization method demonstrated an impressive accuracy of 97.5% on this dataset. These findings show that the model produces beneficial outcomes and may be used by healthcare practitioners as a diagnostic tool. It is important to emphasize that the system’s goal is to augment optometrists’ expertise rather than replace it. In terms of accuracy, the RDS-DR technique fared better than the cutting-edge models VGG19, VGG16, Inception V-3, and Xception. This emphasizes how successful the suggested method is for classifying diabetic retinopathy (DR). Full article

The Internet of Things (IoT) has significantly benefited several businesses, but because of the volume and complexity of IoT systems, there are also new security issues. Intrusion detection systems (IDSs) guarantee both the security posture and defense against intrusions of IoT devices. IoT systems have recently utilized machine learning (ML) techniques widely for IDSs. The primary deficiencies in existing IoT security frameworks are their inadequate intrusion detection capabilities, significant latency, and prolonged processing time, leading to undesirable delays. To address these issues, this work proposes a novel range-optimized attention convolutional scattered technique (ROAST-IoT) to protect IoT networks from modern threats and intrusions. This system uses the scattered range feature selection (SRFS) model to choose the most crucial and trustworthy properties from the supplied intrusion data. After that, the attention-based convolutional feed-forward network (ACFN) technique is used to recognize the intrusion class. In addition, the loss function is estimated using the modified dingo optimization (MDO) algorithm to ensure the maximum accuracy of classifier. To evaluate and compare the performance of the proposed ROAST-IoT system, we have utilized popular intrusion datasets such as ToN-IoT, IoT-23, UNSW-NB 15, and Edge-IIoT. The analysis of the results shows that the proposed ROAST technique did better than all existing cutting-edge intrusion detection systems, with an accuracy of 99.15% on the IoT-23 dataset, 99.78% on the ToN-IoT dataset, 99.88% on the UNSW-NB 15 dataset, and 99.45% on the Edge-IIoT dataset. On average, the ROAST-IoT system achieved a high AUC-ROC of 0.998, demonstrating its capacity to distinguish between legitimate data and attack traffic. These results indicate that the ROAST-IoT algorithm effectively and reliably detects intrusion attacks mechanism against cyberattacks on IoT systems. Full article