Major depressive disorder (MDD) is a global mental health problem that significantly affects individuals’ daily activities. The diagnosis of MDD is a challenging issue due to people’s stigma and less interest in reaching the clinic for healthcare assistance. People prefer to share their thoughts and feelings through text posts on social media platforms. The main aim of this article is to bridge the gap between medical experts and depressed individuals in identifying the symptoms of MDD early to provide effective treatment before it reaches a critical stage. This article creates a “hybrid model of DistilBERT with a convolutional neural network (CNN)—(HDC),” combining the power of two different deep learning architectures, DistilBERT and CNN, along with advances in natural language processing (NLP) to detect symptoms of MDD in alignment with DSM-5 through analyzing content from social networks. Experiments are conducted using standard online tweet data. The data augmentation technique solves data imbalance problems and avoids model-biased predictions. Precision, recall, f1-score, and accuracy are metrics used to evaluate the current technique with other baseline models. Experimental results show that the “HDC” model achieved 94.13% accuracy and outperformed cutting-edge methodologies for detecting depression symptoms.

Abstract In contrast to a conventional virtual machine (VM), a container is a lightweight virtualization technology. Containers are becoming a prominent technology for cloud services because of their portable, scalable, and flexible deployments, especially in the Internet of Things (IoT), smart devices, and fog and edge computing. It is a type of operating system‐level virtualization in which the kernel allows multiple isolated containers to run independently. Container placement (CP) is a nontrivial problem in Container‐as‐a‐Service (CaaS). CP is mapping to a container over virtual machines (VMs) to execute an application. Designing an efficient CP strategy is complex due to several intertwined challenges. These challenges arise from a diverse spectrum of computing resources, like on‐demand and unpredictable fluctuations of IT resources by multiple tenants. In this article, we propose a modified sum‐based container placement algorithm called a multi‐objective optimization‐based container placement algorithm (MSBCPA). In the proposed algorithm, we have considered two metrics: makespan and monetary costs for optimizing available IT resources. We have conducted comprehensive simulation experiments to validate the effectiveness of the proposed algorithm over the CloudSim 4.0 simulator. The proposed optimization algorithm (MSBCPA) aims to minimize the makespan and the execution monetary costs simultaneously. In the simulation, we found that the execution cost and energy consumption cost reduce by 20% to 30% and achieve the best possible cost‐makespan trade‐offs compared to competing algorithms.

Summary Software‐defined networking (SDN) has revolutionized network architectures by decoupling the control plane from the data plane. An intriguing challenge within this paradigm is the strategic placement of controllers and the allocation of switches to optimize network performance and resilience. In the event of a controller failure, the switches are disconnected from the controller until they are reassigned to other active controllers possessing sufficient spare capacity. The reassignment could lead to a significant rise in propagation latency. This correspondence presents a mathematical model for capacitated controller placement, strategically designed to anticipate failures and prevent a substantial increase in worst‐case latency and disconnections. The aim is to minimize the worst‐case latency between switches and their backup controllers and among the controllers. Four metaheuristic algorithms are proposed including, an enhanced genetic algorithm (CCPCFR‐EGA), particle swarm optimization (CCPCFR‐PSO), a hybrid particle swarm optimization and simulated annealing algorithm (CCPCFR‐HPSOSA), and a grey wolf optimization algorithm (CCPCFR‐GWO). These algorithms are compared with a simulated annealing method and an optimal method. Evaluation conducted on four network datasets demonstrates that the proposed metaheuristic methods are faster than the optimal method. The experimental outcome indicates that CCPCFR‐HPSOSA and CCPCFR‐GWO outperform the other methods, consistently providing near‐optimal solutions. However, CCPCFR‐GWO is preferred over CCPCFR‐HPSOSA due to its faster execution time. Specifically, CCPCFR‐GWO achieves an average speed‐up of 3.9 over the optimal for smaller networks and an average speed‐up of 31.78 for larger networks, while still producing near‐optimal solutions.

Abstract Containers in cloud computing provide a logical packaging technique for applications to be isolated from the computing environment in which they actually execute, allowing for efficient sharing of memory, processor, storage, and network resources at the Operating System (OS) level. Since they are so compact, container‐based clouds have recently gained significant popularity. In order to maximize resource usage and minimize energy consumption, the container consolidation technique is widely employed in the cloud environment. This work introduces container consolidation in cloud computing that exploits Fractional Pelican Hawks Optimization (FPHO). In Container as a Service (CaaS) model, containers are placed in the Virtual Machines (VMs), and virtual machines are hosted in Physical Machines (PMs) or servers. The proposed method for container consolidation consists of two modules, namely, the host status module and the consolidation module. In the host status module, the PM's load is predicted using Long Short Term Memory (LSTM) and checked whether the PM is overloaded or underloaded using a threshold. If it is overloaded, the container selection algorithm is performed, and the migration list is also generated. In the consolidation module, the created migration list which is employed for the destination list to be created by an overloaded destination selector. In the same way, the underloaded list is also generated by the underloaded destination selector. Finally, the container and VM migration is carried out by considering the multi‐objectives such as predicted load, migration cost, resource utilization, energy consumption, network, and bandwidth which are optimally selected by the proposed FHPO. Here, FHPO is the combination of Fractional Pelican Optimization (FPO) and Fire Hawk Optimizer (FHO). The designed model achieved the measures with minimum energy consumption, resource utilization, Service Level Agreement (SLA), and Makespan as 0.066, 0.019, 0.054, and 0.066, respectively for setup one.

Depression is a kind of emotion that negatively impacts people's daily lives. The number of people suffering from long-term feelings is increasing every year across the globe. Depressed patients may engage in self-harm behaviors, which occasionally result in suicide. Many psychiatrists struggle to identify the presence of mental illness or negative emotion early to provide a better course of treatment before they reach a critical stage. One of the most challenging problems is detecting depression in people at the earliest possible stage. Researchers are using Natural Language Processing (NLP) techniques to analyze text content uploaded on social media, which helps to design approaches for detecting depression. This work analyses numerous prior studies that used learning techniques to identify depression. The existing methods suffer from better model representation problems to detect depression from the text with high accuracy. The present work addresses a solution to these problems by creating a new hybrid deep learning neural network design with better text representations called “Fasttext Convolution Neural Network with Long Short-Term Memory (FCL).” In addition, this work utilizes the advantage of NLP to simplify the text analysis during the model development. The FCL model comprises fasttext embedding for better text representation considering out-of-vocabulary (OOV) with semantic information, a convolution neural network (CNN) architecture to extract global information, and Long Short-Term Memory (LSTM) architecture to extract local features with dependencies. The present work was implemented on real-world datasets utilized in the literature. The proposed technique provides better results than the state-of-the-art to detect depression with high accuracy.

Summary Serverless computing has emerged as a powerful deployment model based on the Function‐as‐a‐Service (FaaS) paradigm, where applications are orchestrated through a set of independent functions. The function orchestration within an application can be represented through a serverless workflow, which defines the overall execution plan of the application. To ensure the quality of service for serverless computing platforms, it is essential to develop performance and cost models that can predict the service quality that can be obtained from deploying and executing applications in the cloud platform. While several analytical models have been developed for various cloud deployment frameworks in recent years, there has been a lack of performance and cost analysis models for serverless computing platforms. The existing performance and cost monitoring tools available in serverless frameworks face several challenges, such as complexity, lack of transparency, and incomplete monitoring data. In this paper, we fill the gap by proposing an efficient workflow‐based analytical model that can estimate the end‐to‐end response time and cost of the serverless execution plan. The proposed model can handle complex structures like loop, cycles, self‐loop, and parallel substructures that exist in serverless workflows. Additionally, we propose a heuristic optimization algorithm to identify the optimal resource configuration to achieve the optimal response time under a given budget constraint. We evaluated the effectiveness of the proposed model by considering seven serverless applications in both AWS Lambda and Microsoft Azure platforms. We compared the accuracy of the proposed model with the real values of response time and cost obtained in AWS Lambda and Microsoft Azure serverless platforms. The proposed performance and cost model in the AWS Lambda platform has been observed to have an average accuracy of 99.2% and 98.7% respectively. In the Microsoft Azure platform, the average accuracy of the performance and cost model has been observed to be 98.6% and 98.2% respectively.

Cloud computing is a revolutionary paradigm, which allows applications to run in a virtualized environment. The application runs on a virtual cloud resource makes the system scalable and cost-efficient. Noticeably many applications, such as healthcare systems, video streaming, Internet of Things (IoT) running in the cloud, are real-time in nature, i.e., these applications demand responses within a particular time limit, i.e., deadline. To meet the requirement of such applications, a Cloud Service Provider (CSP) must have a sufficient number of cloud resources (virtual machines). Further, the ever-growing demand for applications forces a CSP to deploy more and more cloud resources. Inevitably, the massive count of cloud resources in a cloud data center consumes a tremendous amount of energy. Specifically, it becomes cumbersome to offer services to deadline-sensitive tasks while minimizing energy consumption. An efficient task scheduling is an attractive way to reduce energy usage while ensuring satisfactory services for cloud users. Learning Automata (LA) is a reinforcement-based adaptive decision-making unit that learns and selects the best action from a set of actions applied in a dynamic environment. Similar to LA, in task scheduling, the best task and virtual machine combinations are chosen from a set of available combinations. In this context, this paper implemented the LA technique to solve a bi-objective deadline-sensitive task scheduling problem which includes minimization of energy consumption and makespan. At first, a learning automata-based scheduling framework is designed for deadline-sensitive tasks in the cloud. Later, a scheduling algorithm, namely, the LA-based Scheduling (LAS) algorithm, is proposed. The LAS algorithm exploits the heterogeneity of tasks and virtual machines (VMs) while guaranteeing the task’s deadline. Extensive simulation is carried out to designate the effectiveness and applicability of LAS for deadline-sensitive task scheduling in the heterogeneous cloud environment.

The evolution of cloud computing facilitates applications with varying demands to operate in a virtualized environment. For instance, applications like the healthcare system, video streaming, Internet of Things (IoT) that are moving to the cloud, demand responses within a particular time limit, i.e., deadline. However, the cloud computing system consumes a considerable amount of electric energy while providing services to these type of applications, which in turn contribute to the high operational cost. Specifically, it becomes cumbersome to offer services to deadline sensitive task while minimizing energy consumption. In this regard, efficient task scheduling is an attractive way to cut down energy usage while ensuring satisfactory services for cloud users. In this paper, the task scheduling problem is considered as a bi-objective minimization problem which includes minimization of energy consumption and makespan. First, we proposed a novel learning automata-based scheduling framework for deadline sensitive tasks in the cloud. Learning automata (LA) is an adaptive decision-making unit that helps the scheduler to select the best responses. Later, the LA-based Scheduling (LAS) algorithm is introduced which exploits the heterogeneity of tasks and virtual machines (VMs) while ensuring the timing requirements of the tasks. Extensive simulation is carried out to designate the effectiveness and applicability of LAS for deadline sensitive task scheduling in the heterogeneous cloud environment.

Neural networks are extensively used for determining different characteristics of optical burst switching networks. The main disadvantage of optical burst switching network is burst drop and burst contention, which occurs because of burst getting blocked. Using neural network approaches, blocking probability can be pre-determined for the upcoming traffic. In this paper, Log-incremental modified extreme learning machine trained generalized radial basis function neural network (MELM-GRBFNN) model is used for training and predicting burst contention or burst blocking probability. From the obtained results, it is inferred that the prediction accuracy of our proposed model is more accurate and faster than the contemporary approaches. It is observed that our proposed method is competent in predicting the burst blocking probability with higher accuracy and indicates a reduction in the burst loss. Thus, it will help network designers to have a preliminary idea about the performance of the network model under specific configurations.

In software-defined networks (SDNs), the deployment of multiple controllers improves the reliability and scalability of the distributed control plane. Recently, edge computing (EC) has become a backbone to networks where computational infrastructures and services are getting closer to the end user. The unique characteristics of SDN can serve as a key enabler to lower the complexity barriers involved in EC, and provide better quality-of-services (QoS) to users. As the demand for IoT keeps growing, gradually a huge number of smart devices will be connected to EC and generate tremendous IoT traffic. Due to a huge volume of control messages, the controller may not have sufficient capacity to respond to them. To handle such a scenario and to achieve better load balancing, dynamic switch migrating is one effective approach. However, a deliberate mechanism is required to accomplish such a task on the control plane, and the migration process results in high network delay. Taking it into consideration, this article has introduced an efficient switch migration-based load balancing (ESMLB) framework, which aims to assign switches to an underutilized controller effectively. Among many alternatives for selecting a target controller, a multicriteria decision-making method, i.e., the technique for order preference by similarity to an ideal solution (TOPSIS), has been used in our framework. This framework enables flexible decision-making processes for selecting controllers having different resource attributes. The emulation results indicate the efficacy of the ESMLB.

Software defined networks provides a global network view with centralized management. To maintain the network configuration, multiple controllers are required. The network performance depends on the optimal number of controllers and their placement. Due to the large size and complexity involved, meta-heuristic algorithms are the probable choice that can solve the problems in an acceptable amount of time. This paper addresses the controller placement problem in SDN by using two meta-heuristic techniques. The objective is to find optimal number and location of controllers in the network while minimizing the propagation latency and optimizing cost. A random approach is adopted for initial placement of controllers. The assignment of switches to the controllers is done based on their shortest distance. Then an efficient genetic algorithm based placement solution is proposed to find the optimal location of controllers which minimizes cost. Our proposed genetic algorithm is different from the standard genetic algorithm in terms of generation and replacement for determining the best cost and the optimal location of controllers. The same experiment is done on simulated annealing (SA) and random method. For evaluation purpose, we have used some real topologies. The results of our enhanced GA performs better compared to simulated annealing and random placement approach.

The primary innovations behind Software Defined Networks (SDN)are the decoupling of the control plane from the data plane and centralizing the network management through a specialized application running on the controller. Despite all its capabilities, the introduction of various architectural entities of SDN poses many security threats and potential target. Especially, Distributed Denial of Services (DDoS) is a rapidly growing attack that poses a tremendous threat to both control plane and forwarding plane of SDN. Asthe control layer is vulnerable to DDoS attack, the goal of this paper is to provide a defense system which is based on Learning Automata (LA) concepts. It is a self-operating mechanism that responds to a sequence of actions in a certain way to achieve a specific goal. The simulation results show that this scheme effectively reduces the TCP connection setup delay due to DDoS attack.

Reducing energy consumption in the fog computing environment is both a research and an operational challenge for the current research community and industry. There are several industries such as finance industry or healthcare industry that require a rich resource platform to process big data along with edge computing in fog architecture. As a result, sustainable computing in a fog server plays a key role in fog computing hierarchy. The energy consumption in fog servers depends on the allocation techniques of services (user requests) to a set of virtual machines (VMs). This service request allocation in a fog computing environment is a nondeterministic polynomial-time hard problem. In this paper, the scheduling of service requests to VMs is presented as a bi-objective minimization problem, where a tradeoff is maintained between the energy consumption and makespan. Specifically, this paper proposes a metaheuristic-based service allocation framework using three metaheuristic techniques, such as particle swarm optimization (PSO), binary PSO, and bat algorithm. These proposed techniques allow us to deal with the heterogeneity of resources in the fog computing environment. This paper has validated the performance of these metaheuristic-based service allocation algorithms by conducting a set of rigorous evaluations.

Link prediction is an important research direction in the field of Social Network Analysis.The significance of this research area is crucial especially in the fields of network evolution analysis and recommender system in online social networks as well as e-commerce sites.This paper aims at predicting the hidden links that are likely to occur in near future.The possibility of formation of links is based on the similarity score between pair of nodes that are not yet connected in the social network.The similarity score, which we call link prediction score has been evaluated in Map-Reduce programming model.The proposed similarity score is based on both the structural information around the nodes and the degree of influence for neighboring nodes.The proposed algorithm is scalable in nature and performs quite well for large scale complex networks having good number of nodes and edges based on large pool of data or often termed as big-data.The efficiency and effectiveness of the algorithms are extensively tested and compared against traditional link prediction algorithms using three real world social network datasets.

This paper describes a new radix based calibration technique for pipelined analog-to-digital converters (ADCs). The proposed technique uses sinusoidal signal sampled at Nyquist rate to mitigate the effects of capacitor mismatch and finite op amp gain error that degrade the performance of a typical pipelined ADC. The calibration has been illustrated using a 1.5-bit per stage non-flipover topology. This technique is promising compared to the existing foreground calibration algorithms as it requires sinusoidal input which is easily available. Since this technique does the calibration at Nyquist rate it captures the finite op amp settling effect, which no other foreground calibration technique does. Behavioral simulations for a 12-bit pipelined ADC which has 11, 1.5-bit stages followed by 2-bit flash, validate the calibration technique.