Search

Abstract Data centers are a major source of carbon emissions and are subsequently contributing to global carbon footprints. Keeping in view of providing a sustainable solution to society, we have analyzed various factors that can help to achieve carbon neutrality and maximum sustainability. Our study pointed towards the need to follow a sustainable approach for incoming workflow throughout the life-cycle of Data centers. We analyzed that workloads need to be segregated before assigning them to the data centers so that energy-efficient resource allocation could be done. This paper demonstrates unsupervised learning techniques to cluster the incoming cloud workloads. The heterogeneous workloads were characterized using machine learning approaches and appropriate clusters were crafted. For analysis, Google Cluster Dataset is used. In order to improve the accuracy, data were normalized, and random samples of data were selected for clustering. The machine learning algorithms applied were able to successfully determine the appropriate clusters that can further be used for energy-efficient resource scheduling.

Education is one of the many sectors in which augmented reality has been successfully implemented. To determine how Augmented Reality (AR) supports education, this bibliometric study analyzes 1734 articles extracted from the Scopus database between 2010 and mid-2023. The study aimed to determine patterns in productivity, authorship and collaboration patterns, publications, citation structures, general research tendencies, and bibliographic coupling. Biblioshiny and VOSviewer were employed in this investigation. The outcomes of the study indicate an ongoing trend of increasing publication counts or more contributions since 2016, and still a trending topic studies on interactive learning environments and AR in education and knowledge constitute niche areas, while epidemiology, science education, and mobile augmented reality are important research topics that were underdeveloped and indicate a relationship that is both emerging and declining, based on a thematic analysis of the papers. Furthermore, the outcomes demonstrate that the USA, Spain, and the United Kingdom have the strongest global cooperation despite the USA writing more articles. To offer an ideal road map for scholars who would like to carry out research in this area, this paper also looks at the trendsetting in augmented reality in education.

BackgroundThe occurrence of diseases in rice leaves presents a substantial challenge to farmers on a global scale, hence jeopardizing the food security of an expanding global population. The timely identification and prevention of these diseases are of utmost importance in order to mitigate their impact.MethodsThe present study conducts a comprehensive evaluation of contemporary literature pertaining to the identification of rice diseases, covering the period from 2008 to 2023. The process of selecting pertinent studies followed the guidelines outlined by Kitchenham, which ultimately led to the inclusion of 69 studies for the purpose of review. It is worth mentioning that a significant portion of research endeavours have been directed towards studying diseases such as rice brown spot, rice blast, and rice bacterial blight. The primary performance parameter that emerged in the study was accuracy. Researchers strongly advocated for the combination of hybrid deep learning and machine learning methodologies in order to improve the rates of recognition for rice leaf diseases.ResultsThe study presents a comprehensive collection of scholarly investigations focused on the detection and characterization of diseases affecting rice leaves, with specific emphasis on rice brown spot, rice blast, and rice bacterial blight. The prominence of accuracy as a primary performance measure highlights the importance of precision in the detection and diagnosis of diseases. Furthermore, the efficacy of employing hybrid methodologies that combine deep learning and machine learning techniques is exemplified in enhancing the recognition capacities pertaining to diseases affecting rice leaves.ConclusionThis systematic review provides insight into the significant research endeavours conducted by scholars in the field of rice disease detection during the previous decade. The text underscores the significance of precision in evaluation and calls for the implementation of hybrid deep learning and machine learning methodologies to augment disease identification, presenting possible resolutions to the obstacles presented by these agricultural hazards.

One of the most economical and precious spices ever known is saffron. It has innumerable pharmaceutical applications, and its cultivation is limited to certain topographic regions throughout the world. Although efforts are continuously being made to increase productivity and increase the area under cultivation, there are multiple factors leading to its low production. Corm size is one of the major factors affecting the quality and production of saffron. The more the corm size for a plantation, the better the yield of the crop. This can pose a serious threat to saffron cultivators who are not able to get good quality corms and sort quality corms from infected ones. Additional factors affecting saffron cultivation include attack by fungus leading to corm rots and sclerotineal disease. In this paper, IoT (Internet of Things) has been used to provide an energy-efficient, ready-to-use, reliable, and user-friendly solution for corm sorting and treatment before sowing to promote quality, better yield and minimized wastage due to corm rots. After sorting the corms, they are treated with 0.2% of tiabendazole fungicide solution and dried, before sowing and for long-term storage. Firstly, sorting and treatment system for the saffron corms processing as per weight is proposed. First two-layer cleaning mechanism to remove foreign substances, then three-step treatment has been applied to remove microorganisms. An automated conveyor system equipped with IoT devices was used for sorting and treating saffron corms. Different energy efficient LPWA (Low Power Wide Area) and LTE (Long Term Evolution) technologies used in the framework, for communication are NB-IoT (Narrow Band IoT) and LoRa (Long Range Radio).

The impact of deep learning (DL) is substantial across numerous domains, particularly in agriculture. Within this context, our study focuses on the classification of problematic soybean seeds. The dataset employed encompasses five distinct classes, totaling 5513 images. Our model, based on the InceptionV3 architecture, undergoes modification with the addition of five supplementary layers to enhance efficiency and performance. Techniques such as transfer learning, adaptive learning rate adjustment (to 0.001), and model checkpointing are integrated to optimize accuracy. During initial evaluation, the InceptionV3 model achieved 88.07% accuracy in training and 86.67% in validation. Subsequent implementation of model tuning strategies significantly improves performance. Augmenting the architecture with additional layers, including Average Pooling, Flatten, Dense, Dropout, and Softmax, plays a pivotal role in enhancing accuracy. Evaluation metrics, including precision, recall, and F1-score, underscore the model’s effectiveness. Precision ranges from 0.9706 to 1.0000, while recall values demonstrate a high capture rate across all classes. The F1-score, reflecting a balance between precision and recall, exhibits remarkable performance across all classes, with values ranging from 0.9851 to 1.0000. Comparative analysis with existing studies reveals competitive accuracy of 98.73% achieved by our proposed model. While variations exist in specific purposes and datasets among studies, our model showcases promising performance in soybean seed classification, contributing to advancements in agricultural technology for crop health assessment and management.

Counterfeit drugs pose significant health risks due to their variable efficacy and potential harmful ingredients. To combat this issue, a reliable and secure track-and-trace system is essential for pharmaceutical supply chains. This paper proposes an Immutable and Decentralized Pharma (IDP) model, leveraging blockchain technology to ensure the safe and efficient distribution of medications. The IDP model utilizes smart contracts to record transactions between entities onto a blockchain, enabling end-to-end product tracking and provenance. Experimental results on a polygon blockchain test network demonstrate the feasibility and enhanced security of the IDP model in a collaborative environment. Our solution addresses the challenges of data privacy, openness, and authenticity inherent in centralized track-and-trace systems, providing a promising approach to eliminate counterfeits and guarantee product safety in pharmaceutical supply chains.

The Internet of Things (IoT) is a collection of devices such as sensors for collecting data, actuators that perform mechanical actions on the sensor's collected data, and gateways used as an interface for effective communication with the external world. The IoT has been successfully applied to various fields, from small households to large industries. The IoT environment consists of heterogeneous networks and billions of devices increasing daily, making the system more complex and this need for privacy and security of IoT devices become a major concern. The critical components of IoT are device identification, a large number of sensors, hardware operating systems, and IoT semantics and services. The layers of a core IoT application are presented in this paper with the protocols used in each layer. The security challenges at various IoT layers are unveiled in this review paper along with the existing mitigation strategies such as machine learning, deep learning, lightweight encryption techniques, and Intrusion Detection Systems (IDS) to overcome these security challenges and future scope. It has been concluded after doing an intensive review that Spoofing and Distributed Denial of Service (DDoS) attacks are two of the most common attacks in IoT applications. While spoofing tricks systems by impersonating devices, DDoS attacks flood IoT systems with traffic. IoT security is also compromised by other attacks, such as botnet attacks, man-in-middle attacks etc. which call for strong defenses including IDS framework, deep neural networks, and multifactor authentication system.

An Electric Vehicle (EV) charger or Electric Vehicle Supply Equipment (EVSE) is a piece of equipment that supplies electrical power for charging plug–in electric vehicles. Although batteries can only be charged with Direct Current (DC) power, most electric vehicles have an onboard Alternative Current AC—to—DC converter and most fully electric cars can accept both AC and DC power. The adoption of EVs can bring about significant relief in noise pollution and also environmental pollution if the required electricity is generated using renewable sources. DC charging stations of various levels are commonly equipped with multiple ports of various levels to be able to charge a wide variety of EVs. EVSEs are found at various facilities such as street–side or retail shopping centers, government facilities, and other parking areas. To ensure a sustainable environment by reducing the carbon emissions from vehicles, the use of EVs needs to be promoted. The need for having Electric Vehicle Charging Stations (EVCS) in any region depends upon the demand and cluster density of EVs in that region and is a major factor in the process of promoting the use of EVs and facilitating sustainable tourism using cleaner fuels. The authors of this study have located the various types and numbers of EVSEs throughout all the states and union territories of India, showing the emerging use of EVs so that EV users can conveniently locate charging stations and plan their routes accordingly. Furthermore, other citizens may be encouraged to own and use EVs for better environmental sustainability.

In the era of advancing artificial intelligence (AI), its application in agriculture has become increasingly pivotal. This study explores the integration of AI for the discriminative classification of corn diseases, addressing the need for efficient agricultural practices. Leveraging a comprehensive dataset, the study encompasses 21,662 images categorized into four classes: Broken, Discolored, Silk cut, and Pure. The proposed model, an enhanced iteration of MobileNetV2, strategically incorporates additional layers—Average Pooling, Flatten, Dense, Dropout, and softmax—augmenting its feature extraction capabilities. Model tuning techniques, including data augmentation, adaptive learning rate, model checkpointing, dropout, and transfer learning, fortify the model's efficiency. Results showcase the proposed model's exceptional performance, achieving an accuracy of ~96% across the four classes. Precision, recall, and F1-score metrics underscore the model's proficiency, with precision values ranging from 0.949 to 0.975 and recall values from 0.957 to 0.963. In a comparative analysis with state-of-the-art (SOTA) models, the proposed model outshines counterparts in terms of precision, recall, F1-score, and accuracy. Notably, MobileNetV2, the base model for the proposed architecture, achieves the highest values, affirming its superiority in accurately classifying instances within the corn disease dataset. This study not only contributes to the growing body of AI applications in agriculture but also presents a novel and effective model for corn disease classification. The proposed model's robust performance, combined with its competitive edge against SOTA models, positions it as a promising solution for advancing precision agriculture and crop management.

Radiologists confront formidable challenges when confronted with the intricate task of classifying brain tumors through the analysis of MRI images. Our forthcoming manuscript introduces an innovative and highly effective methodology that capitalizes on the capabilities of Least Squares Support Vector Machines (LS-SVM) in tandem with the rich insights drawn from Multi-Scale Morphological Texture Features (MMTF) extracted from T1-weighted MR images. Our methodology underwent meticulous evaluation on a substantial dataset encompassing 139 cases, consisting of 119 cases of aberrant tumors and 20 cases of normal brain images. The outcomes we achieved are nothing short of extraordinary. Our LS-SVM-based approach vastly outperforms competing classifiers, demonstrating its dominance with an exceptional accuracy rate of 98.97%. This represents a substantial 3.97% improvement over alternative methods, accompanied by a notable 2.48% enhancement in Sensitivity and a substantial 10% increase in Specificity. These results conclusively surpass the performance of traditional classifiers such as Support Vector Machines (SVM), Radial Basis Function (RBF), and Artificial Neural Networks (ANN) in terms of classification accuracy. The outstanding performance of our model in the realm of brain tumor diagnosis signifies a substantial leap forward in the field, holding the promise of delivering more precise and dependable tools for radiologists and healthcare professionals in their pivotal role of identifying and classifying brain tumors using MRI imaging techniques.

One of the most important tasks in handling real-world global optimization problems is to achieve a balance between exploration and exploitation in any nature-inspired optimization method. As a result, the search agents of an algorithm constantly strive to investigate the unexplored regions of a search space. Aquila Optimizer (AO) is a recent addition to the field of metaheuristics that finds the solution to an optimization problem using the hunting behavior of Aquila. However, in some cases, AO skips the true solutions and is trapped at sub-optimal solutions. These problems lead to premature convergence (stagnation), which is harmful in determining the global optima. Therefore, to solve the above-mentioned problem, the present study aims to establish comparatively better synergy between exploration and exploitation and to escape from local stagnation in AO. In this direction, firstly, the exploration ability of AO is improved by integrating Dynamic Random Walk (DRW), and, secondly, the balance between exploration and exploitation is maintained through Dynamic Oppositional Learning (DOL). Due to its dynamic search space and low complexity, the DOL-inspired DRW technique is more computationally efficient and has higher exploration potential for convergence to the best optimum. This allows the algorithm to be improved even further and prevents premature convergence. The proposed algorithm is named DAO. A well-known set of CEC2017 and CEC2019 benchmark functions as well as three engineering problems are used for the performance evaluation. The superior ability of the proposed DAO is demonstrated by the examination of the numerical data produced and its comparison with existing metaheuristic algorithms.

The early detection and preliminary diagnosis of COVID-19 play a crucial role in effectively managing the pandemic. Radiographic images have emerged as valuable tool in achieving this objective. Deep learning techniques, a subset of artificial intelligence, have been extensively employed for the processing and analysis of these radiographic images. Notably, their ability to identify and detect patterns within radiographic images can be extended beyond COVID-19 and can be applied to recognize patterns associated with other pandemics or diseases. This paper seeks to provide an overview of the deep learning techniques developed for detection of corona-virus (COVID-19) based on radiological data (X-Ray and CT images). It also sheds some information on the methods utilized for feature extraction and data preprocessing in this field. The purpose of this study is to make it easier for researchers to comprehend various deep learning techniques that are used to detect COVID-19 and to introduce or ensemble those approaches to prevent the spread of corona virus in future.

In cloud computing environments, virtualization is used to share physical machine (PM) resources among multiple users by creating virtual machines (VMs). Running the PM consumes a large amount of energy. Additionally, the PM will be overloaded when the demand for resources exceeds the PM capacity. This overload on the PM leads to violations of Service Level Agreements (SLAs). Dynamic VM consolidation techniques use live migration of VMs to optimize resource utilization and minimize energy consumption. However, excessive migration of VMs impacts negatively the application performance due to the incurred overhead at the runtime. This paper presents a modified genetic-based VM consolidation (MGVMC) strategy that aims to replace VMs in an online manner taking into account energy consumption, SLA violations, and the number of VM migrations. The MGVMC strategy utilizes the genetic algorithm to migrate VMs to the appropriate PM in a way that minimizes the number of over-utilized and under-utilized physical machines (PMs) as low as possible. The performance of the MGVMC strategy was evaluated using the CloudSim Plus framework with a large number of VMs and workload traces from the PlanetLab platform. The experimental results revealed that the MGVMC strategy achieved a significant improvement in energy consumption, SLA violations, and the number of VM migrations compared to other recent approaches. These results demonstrate the effectiveness of the MGVMC strategy in optimizing VM consolidation in the cloud environment.

The Zero Trust safety architecture emerged as an intriguing approach for overcoming the shortcomings of standard network security solutions. This extensive survey study provides a meticulous explanation of the underlying principles of Zero Trust, as well as an assessment of the many strategies and possibilities for effective implementation. The survey begins by examining the role of authentication and access control within Zero Trust Architectures, and subsequently investigates innovative authentication, as well as access control solutions across different scenarios. It more deeply explores traditional techniques for encryption, micro-segmentation, and security automation, emphasizing their importance in achieving a secure Zero Trust environment. Zero Trust Architecture is explained in brief, along with the Taxonomy of Zero Trust Network Features. This review article provides useful insights into the Zero Trust paradigm, its approaches, problems, and future research objectives for scholars, practitioners, and policymakers. This survey contributes to the growth and implementation of secure network architectures in critical infrastructures by developing a deeper knowledge of Zero Trust.

The Aquila Optimizer (AO) is a metaheuristic algorithm that is inspired by the hunting behavior of the Aquila bird. The AO approach has been proven to perform effectively on a range of benchmark optimization issues. However, the AO algorithm may suffer from limited exploration ability in specific situations. To increase the exploration ability of the AO algorithm, this work offers a hybrid approach that employs the alpha position of the Grey Wolf Optimizer (GWO) to drive the search process of the AO algorithm. At the same time, we applied the quasi-opposition-based learning (QOBL) strategy in each phase of the Aquila Optimizer algorithm. This strategy develops quasi-oppositional solutions to current solutions. The quasi-oppositional solutions are then utilized to direct the search phase of the AO algorithm. The GWO method is also notable for its resistance to noise. This means that it can perform effectively even when the objective function is noisy. The AO algorithm, on the other hand, may be sensitive to noise. By integrating the GWO approach into the AO algorithm, we can strengthen its robustness to noise, and hence, improve its performance in real-world issues. In order to evaluate the effectiveness of the technique, the algorithm was benchmarked on 23 well-known test functions and CEC2017 test functions and compared with other popular metaheuristic algorithms. The findings demonstrate that our proposed method has excellent efficacy. Finally, it was applied to five practical engineering issues, and the results showed that the technique is suitable for tough problems with uncertain search spaces.

Recent developments in IoT, big data, fog and edge networks, and AI technologies have had a profound impact on a number of industries, including medical. The use of AI for therapeutic purposes has been hampered by its inexplicability. Explainable Artificial Intelligence (XAI), a revolutionary movement, has arisen to solve this constraint. By using decision-making and prediction outputs, XAI seeks to improve the explicability of standard AI models. In this study, we examined global developments in empirical XAI research in the medical field. The bibliometric analysis tools VOSviewer and Biblioshiny were used to examine 171 open access publications from the Scopus database (2019–2022). Our findings point to several prospects for growth in this area, notably in areas of medicine like diagnostic imaging. With 109 research articles using XAI for healthcare classification, prediction, and diagnosis, the USA leads the world in research output. With 88 citations, IEEE Access has the greatest number of publications of all the journals. Our extensive survey covers a range of XAI applications in healthcare, such as diagnosis, therapy, prevention, and palliation, and offers helpful insights for researchers who are interested in this field. This report provides a direction for future healthcare industry research endeavors.

From a set of existing tuples, a skyline operator retrieves only a subset, superior tuples that are of a person’s interest and are non-dominant. Processing of queries using the skyline operator is an expensive and exhaustive task. It gets more complicated when skyline queries are applied on partially complete data and databases are distributed over different data centers. Incompleteness in data raises many issues such as compromise on transitivity property and the threat of cyclic dominance to occur within database. To overcome such issues this paper proposes an efficient algorithm called Cloud-based Incomplete Data Skyline algorithm (CIDS) for processing skyline queries over partially complete databases in cloud environment. The algorithm retrieves superior tuples with the aim of reducing domination tests between the tuples, decreasing processing time and reducing the huge amount of data flow from one data center to another. Several experiments have been conducted over different types of datasets, and results have proven that the proposed algorithm outplays the existing algorithms in terms of processing time, domination tests as well as the amount of data flow.

The diagnosis of brain tumors at an early stage is an exigent task for radiologists. Untreated patients rarely survive more than six months. It is a potential cause of mortality that can occur very quickly. Because of this, the early and effective diagnosis of brain tumors requires the use of an automated method. This study aims at the early detection of brain tumors using brain magnetic resonance imaging (MRI) data and efficient learning paradigms. In visual feature extraction, convolutional neural networks (CNN) have achieved significant breakthroughs. The study involves features extraction by deep convolutional layers for the efficient classification of brain tumor victims from the normal group. The deep convolutional neural network was implemented to extract features that represent the image more comprehensively for model training. Using deep convolutional features helps to increase the precision of tumor and non-tumor patient classifications. In this paper, we experimented with five machine learnings (ML) to heighten the understanding and enhance the scope and significance of brain tumor classification. Further, we proposed an ensemble of three high-performing individual ML models, namely Extreme Gradient Boosting, Ada-Boost, and Random Forest (XG-Ada-RF), to derive binary class classification output for detecting brain tumors in images. The proposed voting classifier, along with convoluted features, produced results that showed the highest accuracy of 95.9% for tumor and 94.9% for normal. Compared to individual methods, the proposed ensemble approach demonstrated improved accuracy and outperformed the individual methods.

Sunflower is an important crop that is susceptible to various diseases, which can significantly impact crop yield and quality. Early and accurate detection of these diseases is crucial for implementing appropriate management strategies. In recent years, deep learning techniques have shown promising results in the field of disease classification using image data. This study presents a comparative analysis of different deep-learning models for the classification of sunflower diseases. five widely used deep learning models, namely AlexNet, VGG16, InceptionV3, MobileNetV3, and EfficientNet were trained and evaluated using a dataset of sunflower disease images. The performance of each model was measured in terms of precision, recall, F1-score, and accuracy. The experimental results demonstrated that all the deep learning models achieved high precision, recall, F1-score, and accuracy values for sunflower disease classification. Among the models, EfficientNetB3 exhibited the highest precision, recall, F1-score, and accuracy of 0.979. whereas the other models, ALexNet, VGG16, InceptionV3 and MobileNetV3 achieved 0.865, 0.965, 0.954 and 0.969 accuracy respectively. Based on the comparative analysis, it can be concluded that deep learning models are effective for the classification of sunflower diseases. The results highlight the potential of deep learning in early disease detection and classification, which can assist farmers and agronomists in implementing timely disease management strategies. Furthermore, the findings suggest that models like MobileNetV3 and EfficientNetB3 could be preferred choices due to their high performance and relatively fewer training epochs.

Brain tumor diagnosis at an early stage can improve the chances of successful treatment and better patient outcomes. In the biomedical industry, non-invasive diagnostic procedures, such as magnetic resonance imaging (MRI), can be used to diagnose brain tumors. Deep learning, a type of artificial intelligence, can analyze MRI images in a matter of seconds, reducing the time it takes for diagnosis and potentially improving patient outcomes. Furthermore, an ensemble model can help increase the accuracy of classification by combining the strengths of multiple models and compensating for their individual weaknesses. Therefore, in this research, a weighted average ensemble deep learning model is proposed for the classification of brain tumors. For the weighted ensemble classification model, three different feature spaces are taken from the transfer learning VGG19 model, Convolution Neural Network (CNN) model without augmentation, and CNN model with augmentation. These three feature spaces are ensembled with the best combination of weights, i.e., weight1, weight2, and weight3 by using grid search. The dataset used for simulation is taken from The Cancer Genome Atlas (TCGA), having a lower-grade glioma collection with 3929 MRI images of 110 patients. The ensemble model helps reduce overfitting by combining multiple models that have learned different aspects of the data. The proposed ensemble model outperforms the three individual models for detecting brain tumors in terms of accuracy, precision, and F1-score. Therefore, the proposed model can act as a second opinion tool for radiologists to diagnose the tumor from MRI images of the brain.

Skyline queries have been widely used as an effective query tool in many contemporary database applications. The main concept of skyline queries relies on retrieving the non-dominated tuples in the database which are known skylines. In most database applications, the contents of the databases are dynamic due to the continuous changes made towards the database. Typically, the changes in the contents of the database occur through data manipulation operations (INSERT and/or UPDATE). Performing these operations on the database results in invalidating the most recent skylines before changes are made on the database. Furthermore, the presence of incomplete data in databases becomes frequent phenomena in recent database applications. Data incompleteness causes several challenges on skyline queries such as losing the transitivity property of the skyline technique and the test dominance process between tuples being cyclic. Reapplying skyline technique on the entire updated incomplete database to determine the new skylines is unwise due to the exhaustive pairwise comparisons. Thus, this paper proposes an approach, named Incomplete Dynamic Skyline Algorithm (IDSA) which attempts to determine the skylines on dynamic and incomplete databases. Two optimization techniques have been incorporated in IDSA, namely: pruning and selecting superior local skylines. The pruning process attempts to exploit the derived skylines before the INSERT/UPDATE operation made on the database to identify the new skylines. Moreover, selecting superior local skylines process assists in further eliminating the remaining non-skylines from further processing. These two optimization techniques lead to a large reduction in the number of domination tests due to avoiding re-computing of skylines over the entire updated database to derive the new skylines. Extensive experiments have been accomplished on both real and synthetic datasets, and the results demonstrate that IDSA outperforms the existing solutions in terms of the number of domination tests and the processing time of the skyline operation.

Data incompleteness becomes a frequent phenomenon in a large number of contemporary database applications such as web autonomous databases, big data, and crowd-sourced databases. Processing skyline queries over incomplete databases impose a number of challenges that negatively influence processing the skyline queries. Most importantly, the skylines derived from incomplete databases are also incomplete in which some values are missing. Retrieving skylines with missing values is undesirable, particularly, for recommendation and decision-making systems. Furthermore, running skyline queries on a database with incomplete data raises a number of issues influence processing skyline queries such as losing the transitivity property of the skyline technique and cyclic dominance between the tuples. The issue of estimating the missing values of skylines has been discussed and examined in the database literature. Most recently, several studies have suggested exploiting the crowd-sourced databases in order to estimate the missing values by generating plausible values using the crowd. Crowd-sourced databases have proved to be a powerful solution to perform user-given tasks by integrating human intelligence and experience to process the tasks. However, task processing using crowd-sourced incurs additional monetary cost and increases the time latency. Also, it is not always possible to produce a satisfactory result that meets the user's preferences. This paper proposes an approach for estimating the missing values of the skylines by first exploiting the available data and utilizes the implicit relationships between the attributes in order to impute the missing values of the skylines. This process aims at reducing the number of values to be estimated using the crowd when local estimation is inappropriate. Intensive experiments on both synthetic and real datasets have been accomplished. The experimental results have proven that the proposed approach for estimating the missing values of the skylines over crowd-sourced enabled incomplete databases is scalable and outperforms the other existing approaches.

Skyline queries rely on the notion of Pareto dominance, filter the data items by keeping only those data items that are the best, most preferred, also known as skylines, from a database to meet the user's preferences. Skyline query has been studied extensively and a significant number of skyline algorithms have been proposed, mostly attempt to resolve the optimisation problem that is mainly associated with a reduction in the processing time of skyline computations. In today's era, the presence of incomplete data in a database is inevitable. Furthermore, databases are dynamic in nature in which their states change throughout the time to reflect the current and latest information of the applications. The skylines derived before changes are made towards the initial database are no longer valid in the new state of the database. Blindly examining the entire database to identify the new set of skylines is unwise as not all data items are affected by the changes made towards the database. Hence, in this paper we propose a solution, named DyIn-Skyline, which is capable of deriving skylines over a dynamic and incomplete database, by exploiting only those data items that are affected by the changes. Several experiments have been conducted and the results show that our proposed solution outperforms the previous works with regard to the number of pairwise comparisons and processing time.

Automatic image caption prediction is a challenging task in natural language processing. Most of the researchers have used the convolutional neural network as an encoder and decoder. However, an accurate image caption prediction requires a model to understand the semantic relationship that exists between the various objects present in an image. The attention mechanism performs a linear combination of encoder and decoder states. It emphasizes the semantic information present in the caption with the visual information present in an image. In this paper, we incorporated the Bahdanau attention mechanism with two pre-trained convolutional neural networks—Vector Geometry Group and InceptionV3—to predict the captions of a given image. The two pre-trained models are used as encoders and the Recurrent neural network is used as a decoder. With the help of the attention mechanism, the two encoders are able to provide semantic context information to the decoder and achieve a bilingual evaluation understudy score of 62.5. Our main goal is to compare the performance of the two pre-trained models incorporated with the Bahdanau attention mechanism on the same dataset.

This research aimed to investigate the relationship and the correlation between abdomen fat accumulation and the level of diffused fat in the human liver using computerized methods. Computed tomography data sets of 125 subjects were employed in this study. This investigation was implemented through three phases. For each subject, the quantity of abdomen fat was measured, and then the liver was segmented and analyzed to evaluate the fat content. Finally, the collected results were utilized to evaluate the correlation. In addition, the liver intensities were measured to evaluate the level of the diffused fat in the liver. Experimental results show that there was a medium negative correlation between the visceral fat to the abdomen size ratio and the mean of the liver intensity values. The same correlation was found between the mean of the liver intensity values and the total abdomen fat to the abdomen size ratio. The ratios mentioned above were used to obtain relative measurements for the size contribution of fat (for each type) to the whole size of the abdominal area, due to the wide variety of sizes of subjects used in this research. This study supports the research community with objective measurements that reveal a direct proportional relationship between obesity and the level of diffused fat in the liver. The findings of this research provide evidence of a detrimental health effect of abdominal obesity (especially visceral fat) on liver fat content, which is associated with an increased risk of serious health problems, such as diabetes, high blood pressure, kidney disease, and developing heart problems. The research helps to identify a cause for fat accumulation in the liver, which can help in the process of preventing and treating fatty liver disease.

Given the significance of skyline queries, they are incorporated in various modern applications including personalized recommendation systems as well as decision-making and decision-support systems. Skyline queries are used to identify superior data items in the database. Most of the previously proposed skyline algorithms work on a complete database where the data are always present (non-missing). However, in many contemporary real-world databases, particularly those databases with large cardinality and high dimensionality, such assumption is not necessarily valid. Hence, missing data pose new challenges if the processing skyline queries cannot easily apply those methods that are designed for complete data. This is due to the fact that imperfect data cause the loss of the transitivity property of the skyline method and cyclic dominance. This paper presents a framework called Optimized Incomplete Skyline (OIS) which utilizes a technique that simplifies the skyline process on a database with missing data and helps prune the data items before performing the skyline process. The proposed strategy assures that the number of the domination tests is significantly reduced. A set of experiments has been accomplished using both real and synthetic datasets aimed at validating the performance of the framework. The experiment results confirm that the OIS framework is indeed superior and steadily outperforms the current approaches in terms of the number of domination tests required to retrieve the skylines.

Melanoma skin cancer is considered as one of the most common diseases in the world. Detecting such diseases at early stage is important to saving lives. During medical examinations, it is not an easy task to visually inspect such lesions, as there are similarities between lesions. Technological advances in the form of deep learning methods have been used for diagnosing skin lesions. Over the last decade, deep learning, especially CNN (convolutional neural networks), has been found one of the promising methods to achieve state-of-art results in a variety of medical imaging applications. However, ConvNets’ capabilities are considered limited due to the lack of understanding of long-range spatial relations in images. The recently proposed Vision Transformer (ViT) for image classification employs a purely self-attention-based model that learns long-range spatial relations to focus on the image’s relevant parts. To achieve better performance, existing transformer-based network architectures require large-scale datasets. However, because medical imaging datasets are small, applying pure transformers to medical image analysis is difficult. ViT emphasizes the low-resolution features, claiming that the successive downsampling results in a lack of detailed localization information, rendering it unsuitable for skin lesion image classification. To improve the recovery of detailed localization information, several ViT-based image segmentation methods have recently been combined with ConvNets in the natural image domain. This study provides a comprehensive comparative study of U-Net and attention-based methods for skin lesion image segmentation, which will assist in the diagnosis of skin lesions. The results show that the hybrid TransUNet, with an accuracy of 92.11% and dice coefficient of 89.84%, outperforms other benchmarking methods.

Modeling low level features to high level semantics in medical imaging is an important aspect in filtering anatomy objects. Bag of Visual Words (BOVW) representations have been proven effective to model these low level features to mid level representations. Convolutional neural nets are learning systems that can automatically extract high-quality representations from raw images. However, their deployment in the medical field is still a bit challenging due to the lack of training data. In this paper, learned features that are obtained by training convolutional neural networks are compared with our proposed hand-crafted HSIFT features. The HSIFT feature is a symmetric fusion of a Harris corner detector and the Scale Invariance Transform process (SIFT) with BOVW representation. The SIFT process is enhanced as well as the classification technique by adopting bagging with a surrogate split method. Quantitative evaluation shows that our proposed hand-crafted HSIFT feature outperforms the learned features from convolutional neural networks in discriminating anatomy image classes.

Skyline queries is a rich area of research in the database community. Due to its great benefits, it has been integrated into many database applications including but not limited to personalized recommendation, multi-objective, decision support and decision-making systems. Many variations of skyline technique have been proposed in the literature addressing the issue of handling skyline queries in incomplete database. Nevertheless, these solutions are designed to fit with centralized incomplete database single access. However, in many real-world database systems, this might not be the case, particularly for a database witha large amount of incomplete data distributed over various remote locations such as cloud databases. It is inadequate to directly apply skyline solutions designed for the centralized incomplete database to work on cloud due to the prohibitive cost. Thus, this paper introduces a new approach called Incomplete-data Cloud Skylines (ICS) aiming at processing skyline queries in cloud databases with incomplete data. This approach emphasizes on reducing the amount of data transfer and domination tests during skyline process. It incorporates sorting technique that assists in arranging the data items in a way where dominating data items will be placed at the top of the list helping in eliminate dominated data items. Besides, ICS also employs a filtering technique to prune the dominated data items before applying skyline technique. It comprises a technique named local skyline joiner that helps in reducing the amount of data transfer between datacenters when deriving the final skylines. It limit the amount of data items to be transferred to only those local skylines of each relation. A comprehensive experiment have been performed on both synthetic and real-life datasets, which demonstrate the effectiveness and versatility of our approach in comparison to the current existing approaches. We argue that our approach is practical and can be adopted in many contemporary cloud database systems with incomplete data to process skyline queries.

Distributed Denial of Service (DDoS) attack is a major threat impeding service to legitimate requests on any network. Although the first DDoS attack was reported in 1996, the complexity and sophistication of these attacks has been ever increasing. A 2 TBps attack was reported in mid-August 2020 directed towards critical infrastructure, such as finance, amidst the COVID-19 pandemic. It is estimated that these attacks will double, reaching over 15 million, in the next 2 years. A number of mitigation schemes have been designed and developed since its inception but the increasing complexity demands advanced solutions based on emerging technologies. Blockchain has emerged as a promising and viable technology for DDoS mitigation. The inherent and fundamental characteristics of blockchain such as decentralization, internal and external trustless attitude, immutability, integrity, anonymity and verifiability have proven to be strong candidates, in tackling this deadly cyber threat. This survey discusses different approaches for DDoS mitigation using blockchain in varied domains to date. The paper aims at providing a comprehensive review, highlighting all necessary details, strengths, challenges and limitations of different approaches. It is intended to serve as a single platform to understand the mechanics of current approaches to enhance research and development in the DDoS mitigation domain.

Over the last few years, the research into agriculture has gained momentum, showing signs of rapid growth. The latest to appear on the scene is bringing convenience in how agriculture can be done by employing various computational technologies. There are lots of factors that affect agricultural production, with seed quality topping the list. Seed classification can provide additional knowledge about quality production, seed quality control and impurity identification. The process of categorising seeds has been traditionally done based on characteristics like colour, shape and texture. Generally, this is performed by specialists by visually inspecting each sample, which is a very tedious and time-consuming task. This procedure can be easily automated, providing a significantly more efficient method for seed sorting than having them be inspected using human labour. In related areas, computer vision technology based on machine learning (ML), symmetry and, more particularly, convolutional neural networks (CNNs) have been generously applied, often resulting in increased work efficiency. Considering the success of the computational intelligence methods in other image classification problems, this research proposes a classification system for seeds by employing CNN and transfer learning. The proposed system contains a model that classifies 14 commonly known seeds with the implication of advanced deep learning techniques. The techniques applied in this research include decayed learning rate, model checkpointing and hybrid weight adjustment. This research applies symmetry when sampling the images of the seeds during data formation. The application of symmetry generates homogeneity with regards to resizing and labelling the images to extract their features. This resulted in 99% classification accuracy during the training set. The proposed model produced results with an accuracy of 99% for the test set, which contained 234 images. These results were much higher than the results reported in related research.

A binary grammar is a relational grammar with two nonterminal alphabets, two terminal alphabets, a set of pairs of productions and the pair of the initial nonterminals that generates the binary relation, i.e., the set of pairs of strings over the terminal alphabets. This paper investigates the binary context-free grammars as mutually controlled grammars: two context-free grammars generate strings imposing restrictions on selecting production rules to be applied in derivations. The paper shows that binary context-free grammars can generate matrix languages whereas binary regular and linear grammars have the same power as Chomskyan regular and linear grammars.