Search

Due to the limited availability of training data, the diverse shapes of brain tumors among different patients, inter-class similarity, and intra-class variation, achieving high recognition accuracy and speed in deep learning-based brain tumor recognition remains challenging. To address these issues, we propose a Dual-Branch Ensemble and Gated Global-Local Attention network based on EfficientNetV2S and ConvNeXt (GGLA-NeXtE2NET) to improve identification accuracy and model interpretability. For inter-class and intra-class problems, we designed a Gated Global-Local Attention (GGLA) mechanism that captures dependency information of query points in both horizontal and vertical directions, thereby obtaining global information indirectly. Simultaneously, local information is captured through multiple convolutions with a gating layer. The gating mechanism within the GGLA dynamically balances the contributions of global and local information, enabling the model to adaptively focus on the most relevant features for accurate classification. Furthermore, we introduce a dual-branch ensemble network to address the issue of image variety. This network uses two branches to extract image features at different resolutions for fusion, thereby expanding the network receptive field. Additionally, we utilized an Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) to generate images that balance MRI data and implemented multiple preprocessing techniques to tackle inherent noise in MRI images. These techniques enhance the clarity of MRI images while preserving essential details. This results in a clear improvement in the identification of tumor boundaries, crucial for accurate surgical planning and treatment strategies. We evaluated GGLA-NeXtE2NET on 3-class and 4-class brain tumor datasets and achieved 99.06%, and 99.62% overall accuracy on both datasets respectively.

Abstract Depression is a serious mental state that negatively impacts thoughts, feelings, and actions. Social media use is rapidly growing, with people expressing themselves in their regional languages. In Pakistan and India, many people use Roman Urdu on social media. This makes Roman Urdu important for predicting depression in these regions. However, previous studies show no significant contribution in predicting depression through Roman Urdu or in combination with structured languages like English. The study aims to create a Roman Urdu dataset to predict depression risk in dual languages [Roman Urdu (non‐structural language) + English (structural language)]. Two datasets were used: Roman Urdu data manually converted from English on Facebook, and English comments from Kaggle. These datasets were merged for the research experiments. Machine learning models, including Support Vector Machine (SVM), Support Vector Machine Radial Basis Function (SVM‐RBF), Random Forest (RF), and Bidirectional Encoder Representations from Transformers (BERT), were tested. Depression risk was classified into not depressed, moderate, and severe. Experimental studies show that the SVM achieved the best result with anaccuracy of 0.84% compared to existing models. The presented study refines thearea of depression to predict the depression in Asian countries.

We analyze the nonlinear (2+1)-dimensional KdV–mKdV equation with Caputo fractal–fractional operator. Some theoretical features are demonstrated via fixed point results. The solution of the considered KdV–mKdV is studied by the composition of the J-transformation and decomposition method. For the validity and effectiveness of the considered method, two examples with suitable initial conditions are solved, where best agreements observed. The validity of the suggested approach is verified by convergence analysis and Picard stability. From the simulations of the obtained results, it is noted that fractional order and fractal dimension significantly affects the amplitude and shape of wave solutions.

In this paper, we present a new highly efficient numerical algorithm for nonlinear variable-order space fractional reaction–diffusion equations. The algorithm is based on a new method developed by using the Gaussian quadrature pole rational approximation. A splitting technique is used to address the issues related to computational efficiency and the stability of the method. Two linear systems need to be solved using the same real-valued discretization matrix. The stability and convergence of the method are discussed analytically and demonstrated through numerical experiments by solving test problems from the literature. The variable-order diffusion effects on the solution profiles are illustrated through graphs. Finally, numerical experiments demonstrate the superiority of the presented method in terms of computational efficiency, accuracy, and reliability.

The aim of the article is two-fold. We first analyze and investigate free convective, unsteady, MHD blood flow with single- and multiwalled carbon nanotubes (S&MWCNTs) as nanoparticles. The blood flow has been taken across an upright vertical plate, oscillating in its own plane, and engrafted in a porous medium with slip, radiation, and porosity effects. Nanofluids consist of human blood as the base fluid and SWCNTs and MWCNTs as nanoparticles. The second aim is to discuss the three different definitions of fractional derivatives, namely, Caputo (C), Caputo–Fabrizio (CF), and Atangana–Baleanu (ABC), to obtain the solutions of such proposed models by the Adomian decomposition method. The impact of fractional and physical parameters on the concentration, velocity, and temperature of human blood in the presence of the slip effect is studied and projected diagrammatically. The article ends by providing numerical results such as the reliableness, efficiency, and significant features that are simple in computation with eminent accuracy of the process for non-Newtonian Casson nanofluid fractional order models. It is observed that the velocity of the fluid decreases with SWCNTs’ and MWCNTs’ volume fraction, and an increase in the CNTs’ volume fraction increases blood temperature, which ultimately enhances heat transfer rates. The results acquired are in excellent correspondence with the reported results.

The higher dimensional Fokas equation is the integrable expansion of the Kadomtsev-Petviashvili (KP) and Davey-Stewartson (DS) equations. The Fokas model has an important role in wave theory, to describe the physical phenomena of waves on the surface and inside the water. This article deals with the (4+1)-dimensional conformable space-time fractional-order Fokas partial differential equation. Two efficient methods, namely the generalized exp(-ϕ(ξ))-expansion and improved F-expansion methods, are formulated for conformable fractional-order partial differential equation and new wave structures of fractional order Fokas model are constructed. The different kinds of new solitons are achieved such as bright soliton, dark soliton, Kink and anti-kink solitons, periodic solitary waves, and traveling waves. These new soliton waves are constructed at some values of fractional order α and using different parametric values of the methods by using the software package Mathematica. Newly obtained soliton solutions are compared with the available soliton solutions with different fractional derivatives in the literature. Some of the achieved results are explained 2D and 3D graphically. The new results interpreting that these obtained solutions can be a part, to complete the family of solutions and considered methods are effective, simple, and easy to use. Furthermore, this paper gives an idea, how can reduce the conformable fractional order higher dimensional partial differential equation into an ODE of one variable to obtain the exact solutions. These results and methods can be help to investigate the other higher-dimensional conformable fractional-order models which appear in nonlinear wave theory such as optics, quantum gases, hydrodynamics, photonics, plasmas, and solid-state physics.

The physics of the (4 + 1)-dimensional Fokas equation follows necessarily from the physical nature of the Kadomtsev–Petviashvili and Davey-Stewartson equations in wave theory. In this article, we consider the nonlinear (4+1)-dimensional Fokas partial differential equation. Two recognizable methods namely improved F-expansion and generalized exp(-ϕ(ξ))-expansion methods are proposed to investigate the new wave structures of (4 + 1)-dimensional Fokas dynamical model which have never been constructed before. As a result, new solutions are in different solitons such as dark soliton, bright soliton, combined dark-bright soliton solutions, periodic, and solitary wave solutions. The new generalized solitary wave solutions can be constructed by assigning the specific values to those parameters involved in these methods. The achieved results are compared with existing results in the literature and we found that some of results are not available in literature. The derived results are explained graphically, to understand the phenomena of the proposed model. The constructed results rendering that the consider methods in this article are simple, effective, and easy to find the solution of many other nonlinear higher-dimensional models which arise in several areas of science and engineering.

In this paper, we propose a new SAIR model to depict the transmission dynamics of a novel coronavirus in China. We focus on the ability of asymptomatic COVID-19 patients to transmit and the potential impact of population movements on renewed outbreak transmission. Qualitative analysis of the model shows that when the basic productive number R0>1, the system will stabilize towards a unique endemic equilibrium and pass through a transcritical bifurcation around its disease-free equilibrium. Furthermore, by constructing an appropriate Lyapunov function, we prove that the disease-free equilibrium and endemic equilibrium are globally asymptotically stable under appropriate parameter conditions. Finally, some important results have been verified by numerical simulations.

For conserving energy, duty cycle is defined by setting up the active and sleep periods of network nodes. In beacon enabled networks, to provide support for duty cycle, the IEEE 802.15.4 standard uses optional super-frame structure. This duty cycle is usually fixed and does not consider the topology changes that often occur in dynamic sensor networks. In this paper, existing energy conserving duty cycling approaches for 802.15.4 networks especially the adaptive duty cycling techniques for wireless sensor networks are summed up. Also, this paper highlights the shortcomings of the proposals in the literature, such as induced additional latency, so that they may not support the practical scenarios of Internet of Things (IoT). Further, this study highlights a gross shortcoming that relative performance comparison of RL-based proposals cannot be performed without using a benchmarking framework and real test-bed environment. In this paper, we have presented the future research directions that would lay the foundation for successful development of energy efficient RL-based duty-cycling techniques.

Sparseness is the distinctive aspect of big data generated by numerous applications at present. Furthermore, several similar records exist in real-world sparse datasets. Based on Iterative Trimmed Transaction Lattice (ITTL), the recently proposed TRICE algorithm learns frequent itemsets efficiently from sparse datasets. TRICE stores alike transactions once, and eliminates the infrequent part of each distinct transaction afterward. However, removing the infrequent part of two or more distinct transactions may result in similar trimmed transactions. TRICE repeatedly generates ITTLs of similar trimmed transactions that induce redundant computations and eventually, affects the runtime efficiency. This paper presents D-GENE, a technique that optimizes TRICE by introducing a deferred ITTL generation mechanism. D-GENE suspends the process of ITTL generation till the completion of transaction pruning phase. The deferral strategy enables D-GENE to generate ITTLs of similar trimmed transactions once. Experimental results show that by avoiding the redundant computations, D-GENE gets better runtime efficiency. D-GENE beats TRICE, FP-growth, and optimized versions of SaM and RElim algorithms comprehensively, especially when the difference between distinct transactions and distinct trimmed transactions is high.

It is renowned fact that the study of nonlinear partial differential equations (NPDEs) play a vital rule in cosmic phenomena, atomic and matter physics, that is why researchers have a keen interest to study and find their solutions. Sharma–Tasso–Olever equation is such type of an important equation. In this article, we consider the fractional-order Sharma–Tasso–Olever equation with non-singular Atangana–Baleanu derivative and utilize three remarkable analytical methods, namely, the homotopy perturbation method (HPM), the homotopy perturbation method with Laplace transform (HPLM), and the Adomian decomposition method (ADM), for obtaining the rational solutions. To get a better understanding of this new derivative operator with these methods, the achieved results are compared with the existing results in the literature of Caputo derivative. The numerical results reveal the efficiency, reliability, significant features, and simple in computation with high accuracy by using Atangana–Baleanu derivative with these three approaches. These three methods can be used to find the analytical solutions of many other fractional order problems with Atangana–Baleanu derivative in science and engineering.

Cloud computing emerged as one of the leading computational paradigms due to elastic resource provisioning and pay-as-you-go model. Large data centers are used by the service providers to host the various services. These data centers consume enormous energy, which leads to increase in operating costs and carbon footprints. Therefore, green cloud computing is a necessity, which not only reduces energy consumption, but also affects the environment positively. In order to reduce the energy consumption, workload consolidation approach is used that consolidates the tasks in minimum possible servers. However, workload consolidation may lead to service level agreement (SLA) violations due to non-availability of resources on the server. Therefore, workload consolidation techniques should consider the aforementioned problem. In this paper, we present two consolidation based energy-efficient techniques that reduce energy consumption along with resultant SLA violations. In addition to that, we also enhanced the existing Enhanced-Conscious Task Consolidation (ECTC) and Maximum Utilization (MaxUtil) techniques that attempt to reduce energy consumption and SLA violations. Experimental results show that the proposed techniques perform better than the selected heuristic based techniques in terms of energy, SLA, and migrations.

Sparseness is often witnessed in big data emanating from a variety of sources, including IoT, pervasive computing, and behavioral data. Frequent itemset mining is the first and foremost step of association rule mining, which is a distinguished unsupervised machine learning problem. However, techniques for frequent itemset mining are least explored for sparse real-world data, showing somewhat comparable performance. On the contrary, the methods are adequately validated for dense data and stand apart from each other in terms of performance. Hence, there arises an immense need for evaluating these techniques as well as proposing new ones for large sparse real-world datasets. In this study, a novel method: Mining Frequent Itemsets by Iterative TRimmed Transaction lattICE (TRICE) is proposed. TRICE iteratively generates combinations of varying-sized trimmed subsets of I, where I denote the set of distinct items in a database. Extensive experiments are conducted to assess TRICE against HARPP, FP-Growth, optimized SaM, and optimized RElim algorithms. The experimental results show that TRICE outperforms all these algorithms both in terms of running time and memory consumption. TRICE maintains a substantial performance gap for all sparse real-world datasets on all minimum support thresholds. Moreover, assessment of memory use of optimized SaM and RElim algorithms has been performed for the first time.

In the theory of differential equations, the study of existence and the uniqueness of the solutions are important. In the last few decades, many researchers have had a keen interest in finding the existence–uniqueness solution of constant fractional differential equations, but literature focusing on variable order is limited. In this article, we consider a Caputo type variable order fractional differential equation. First, we present the existence–uniqueness of a solution of the considered problem. Secondly, By borrowing the idea from the theory of ordinary differential equations, we extend the continuation theorem for the variable order fractional differential equation. Further, we prove the global existence results. Finally, we present different types of Ulam–Hyers stability results, which have never been studied before for the Caputo type variable order fractional differential equation.

Data and information security is considered to be an important and challenging task for any field of life. But it becomes more critical especially when it deals with the medical field due to life and health hazards. The ratio of internal security threats to external threats always remains high. A huge number of efforts and technical expertise are required in the case of attacking the system from the external environment. But it requires fewer efforts if a system is attacked internally by the stakeholders of the system. This article presents an access control model that secures the medical data of patients against internal cybersecurity threats. It allows only the legitimate users, that is, authorized patients and doctors to communicate despite the fact of physical boundaries. The proposed model implements authorization in combination with permissions and roles instead of roles only for medical staff. It removes the discrepancies in the existing access control models. The proposed model ensures communication among doctors and patients in a secure, private, and efficient manner. The model is demonstrated by using mathematical modeling along with implementation examples. The proposed model outperformed in comparison with state-of-the-art access control models.

In this article, we consider a fractional differential equation (FDE) with Caputo derivative and study the existence and continuation of its solution. Firstly, we prove a theorem on the existence of local solutions. Then we extend the continuation theorems for ODEs to those FDEs. Also several global existence results for FDE are obtained.

The edit distance between two sequences is the minimum number of weighted transformation-operations that are required to transform one string into the other. The weighted transformation-operations are insert, remove, and substitute. Dynamic programming solution to find edit distance exists but it becomes computationally intensive when the lengths of strings become very large. This work presents a novel parallel algorithm to solve edit distance problem of string matching. The algorithm is based on resolving dependencies in the dynamic programming solution of the problem and it is able to compute each row of edit distance table in parallel. In this way, it becomes possible to compute the complete table in min(m,n) iterations for strings of size m and n whereas state-of-the-art parallel algorithm solves the problem in max(m,n) iterations. The proposed algorithm also increases the amount of parallelism in each of its iteration. The algorithm is also capable of exploiting spatial locality while its implementation. Additionally, the algorithm works in a load balanced way that further improves its performance. The algorithm is implemented for multicore systems having shared memory. Implementation of the algorithm in OpenMP shows linear speedup and better execution time as compared to state-of-the-art parallel approach. Efficiency of the algorithm is also proven better in comparison to its competitor.