Search results

This paper tactics to implement the attack detection in medical Internet of things (IoT) devices using improved deep learning architecture for accomplishing the concept bring your own device (BYOD). Here, a simulation-based hospital environment is modeled where many IoT devices or medical equipment are communicated with each other. The node or the device, which is creating the attack are recognized with the support of attribute collection. The dataset pertaining to the attack detection in medical IoT is gathered from each node that is considered as features. These features are subjected to a deep belief network (DBN), which is a part of deep learning algorithm. Despite the existing DBN, the number of hidden neurons of DBN is tuned or optimized correctly with the help of a hybrid meta-heuristic algorithm by merging grasshopper optimization algorithm (GOA) and spider monkey optimization (SMO) in order to enhance the accuracy of detection. The hybrid algorithm is termed as local leader phase-based GOA (LLP-GOA). The DBN is used to train the nodes by creating the data library with attack details, thus maintaining accurate detection during testing.

This paper has presented novel attack detection in medical IoT devices using improved deep learning architecture as BYOD. With this, this paper aims to show the high convergence and better performance in detecting attacks in the hospital network.

From the analysis, the overall performance analysis of the proposed LLP-GOA-based DBN in terms of accuracy was 0.25% better than particle swarm optimization (PSO)-DBN, 0.15% enhanced than grey wolf algorithm (GWO)-DBN, 0.26% enhanced than SMO-DBN and 0.43% enhanced than GOA-DBN. Similarly, the accuracy of the proposed LLP-GOA-DBN model was 13% better than support vector machine (SVM), 5.4% enhanced than k-nearest neighbor (KNN), 8.7% finer than neural network (NN) and 3.5% enhanced than DBN.

This paper adopts a hybrid algorithm termed as LLP-GOA for the accurate detection of attacks in medical IoT for improving the enhanced security in healthcare sector using the optimized deep learning. This is the first work which utilizes LLP-GOA algorithm for improving the performance of DBN for enhancing the security in the healthcare sector.

This paper aim to find optimal cluster head and minimize energy wastage in WSNs. Wireless sensor networks (WSNs) have low power sensor nodes that quickly lose energy. Energy efficiency is most important factor in WSNs, as they incorporate limited sized batteries that would not be recharged or replaced. The energy possessed by the sensor nodes must be optimally used so as to increase the lifespan. The research is proposing hybrid artificial bee colony and glowworm swarm optimization [Hybrid artificial bee colony and glowworm swarm optimization (HABC-GSO)] algorithm to select the cluster heads. Previous research has considered fitness-based glowworm swarm with Fruitfly (FGF) algorithm, but existing research was limited to maximizing network lifetime and energy efficiency.

The proposed HABC-GSO algorithm selects global optima and improves convergence ratio. It also performs optimal cluster head selection by balancing between exploitation and exploration phases. The simulation is performed in MATLAB.

The HABC-GSO performance is evaluated with existing algorithms such as particle swarm optimization, GSO, Cuckoo Search, Group Search Ant Lion with Levy Flight, Fruitfly Optimization algorithm and grasshopper optimization algorithm, a new FGF in the terms of alive nodes, normalized energy, cluster head distance and delay.

This research work is original.

Wireless Body Area Network (WBAN) technology envisions a network in which sensors continuously operate on and obtained critical physical and physiological readings. Sensors deployed in WBANs have restricted resources such as battery energy, computing power and bandwidth. We can utilize these resources efficiently. By devising a mechanism that is energy efficient with following characteristics, i.e. computational complexity is less, routing overhead is minimized, and throughput will be maximum. A lot of work has been done in this area but still WBAN faces some challenges like mobility, network lifetime, transmission range, heterogeneous environment, and limited resources. In the present years well, contemplative studies have been made through a large body to reach some holistic points pertaining to the energy consumption in WBAN. Thus we/put forward appropriate algorithm for energy efficiency which can vividly corroborate the advances in this specific domain. We have also focused on various aspects and phases of the studies like study computational complexity, routing overhead and throughput type of characteristics. There is still a room for improvement to get the desired energy optimization in WBAN. The network performance mainly relies upon the algorithm used for optimization process. In this work, we intended to develop an energy optimization algorithm for energy consumption in WBAN which is based on evolutionary algorithms for inter-BAN communications using cluster-based routing protocol.

In this paper we propose a meta heuristics algorithm Goa to solve the optimization problem in WBAN. Grasshopper is an insect. Generally, this insect is viewed individually and creating large swarm in nature. Figure 5 shows the individual grasshoppers' primitive patterns in swarm. Figure 7 depicts the pseudo code of Goa. In Goa, experiments are done to view the behavior of grasshoppers in swarm. How they gradually move towards the stationary and mobile target. Through experimentation it is conceived that swarm gradually converge towards their target. Another interesting pattern related to convergence of grasshopper is that it slowly towards its target. This shows that grasshopper does not trapped in local optima. In starting iterations of exploration process Goa, search globally and in last iterations it searches local optima. Goa makes the exploration and exploitation process balanced while solving challenging optimization problems.

Energy efficiency is achieved in the optimization process of cluster formation process. As the use of proposed algorithm Goa creates the optimal number of clusters. Shorter cluster lifetime means more times clustering procedure is called. It increases the network computational cost and the communication overhead. Experimentation results show that proposed Goa algorithm performs well. We compare the results of Goa with existing optimization Algorithms ACO and MFO. Results are generated using MATLAB.

A lot of work has done for the sake of energy optimization in WBAN. Many algorithms are proposed in past for energy optimization of WBAN. All of them have some strengths and weaknesses. In this paper we propose a nature inspired algorithm Goa. We use the Goa algorithm for the sake of energy optimization in WBAN.

The puspose of this paper, a novel systematic design of fractional order proportional integral derivative (FOPID) controller-based speed control of sensorless brushless DC (BLDC) motor using multi-objective enhanced genetic algorithm (EGA). This scheme provides an excellent dynamic and static response, low computational burden, the robust speed control.

The EGA is a meta-heuristic-inspired algorithm for solving non-linearity problems such as sudden load disturbances, modeling errors, power fluctuations, poor stability, the maximum time of transient processes, static and dynamic errors. The conventional genetic algorithm (CGA) and modified genetic algorithm (MGA) are not very effective in solving the above-mentioned problems. Hence, a multi-objective EGA optimized FOPID (EGA-FOPID) controller is proposed for speed control of sensorless BLDC motor under various conditions such as constant load conditions, varying load conditions, varying set speed (Ns) conditions, integrated conditions and controller parameters uncertainty.

This systematic design of the multi-objective EGA-FOPID controller is implemented in MATLAB 2020a with Simulink models for optimal speed control of the BLDC motor. The overall performance of the EGA-FOPID controller is observed and evaluated for computational burden, time integral performance indexes, transient and steady-state characteristics. The hardware experiment results confirm that the proposed EGA-FOPID controller can precisely change the BLDC motor speed is desired range with minimal effort.

The conventional real time issues such as nonlinearity characteristics, poor controllability and stability.

It is clearly evident that out of these three intelligent controllers, the EGA optimized FOPID controller gives enhanced performance by minimizing the time domain parameters, performance Indices error and convergence time. Also, the hardware experimental setup and the results of the proposed EGA-FOPID controller are presented.

It shows the effectiveness of the proposed controllers is completely verified by comparing the above three intelligent optimization algorithms. It is clearly evident that out of these three intelligent controllers, the EGA optimized FOPID controller gives enhanced performance by minimizing the time domain parameters, performance Indices error and convergence time. Also, the hardware experimental setup and the results of the proposed EGA-FOPID controller are presented.

The goal of this study is to determine the values of the process parameters that should be used during the machining of ceramic tile using the abrasive water jet (AWJ) process in order to achieve the lowest possible values for surface roughness and kerf taper angle.

In the present work, ceramic tile is processed by the AWJ process and experimental data were recorded using the RSM approach based Box–Behnken design matrix. The input process factors were water jet pressure, jet traverse speed, abrasive flow rate and standoff distance, to determine the surface roughness and kerf taper angle. ANOVA was used to check the adequacy of model and significance of process parameters. Further, the elite opposition-based learning grasshopper optimization (EOBL-GOA) algorithm was implemented to identify the simultaneous optimization of multiple responses of surface roughness and kerf taper angle in AWJ.

The suggested EOBL-GOA algorithm is suitable for AWJ of ceramic tile, as evidenced by the error rate of ±2 percent between experimental and predicted solutions. The surfaces were evaluated with an SEM to assess the quality of the surface generated with the optimal settings. As compared with initial setting of the SEM image, it was noticed that the bottom cut surface was nearly smooth, with less cracks, striations and pits in the improved optimal results of the SEM image. The results of the analysis can be used to control machining parameters and increase the accuracy of AWJed components.

The findings of this study present an innovative method for assessing the characteristics of the nontraditional machining processes that are most suited for use in industrial and commercial applications.

Advanced big data analysis and machine learning methods are concurrently used to unleash the value of the data generated by government hotline and help devise intelligent applications including automated process management, standard construction and more accurate dispatched orders to build high-quality government service platforms as more widely data-driven methods are in the process.

In this study, based on the influence of the record specifications of texts related to work orders generated by the government hotline, machine learning tools are implemented and compared to optimize classify dispatching tasks by performing exploratory studies on the hotline work order text, including linguistics analysis of text feature processing, new word discovery, text clustering and text classification.

The complexity of the content of the work order is reduced by applying more standardized writing specifications based on combining text grammar numerical features. So, order dispatch success prediction accuracy rate reaches 89.6 per cent after running the LSTM model.

The proposed method can help improve the current dispatching processes run by the government hotline, better guide staff to standardize the writing format of work orders, improve the accuracy of order dispatching and provide innovative support to the current mechanism.

This study aims to compare the performance of two nature-inspired metaheuristics inside Grasshopper in optimizing daylighting and energy performance against brute force in terms of the resemblance to ideal solution and calculation time.

The simulation-based optimization process was controlled using two population-based metaheuristic algorithms, namely, the genetic algorithm (GA) and particle swarm optimization (PSO). The objectives of the optimization routine were optimizing daylighting and energy consumption of a standard reference office while varying the urban context configuration in Alexandria, Egypt.

The results from the GA and PSO were compared to those from brute force. The GA and PSO demonstrated much faster performance to converge to design solution after conducting only 25 and 43% of the required simulation runs, respectively. Also, the average proportion of the resulted weighted sum optimization (WSO) per case using the GA and PSO to that from brute force algorithm was 85 and 95%, respectively.

The work of this paper goes beyond the current practices for showing that the performance of the optimization algorithm can differ by changing the urban context configuration while solving the same problem under the same design variables and objectives.

Currently, more renewable energy resources with advanced technology levels are incorporated in the electric power networks. Under this circumstance, the attainment of optimal economic dispatch is very much essential by the power system as the system requires more power generation cost and also has a great demand for electrical energy. Therefore, one of the primary difficulties in the power system is lowering the cost of power generation, which includes both economic and environmental costs. This study/paper aims to introduce a meta-heuristic algorithm, which offers an solution to the combined economic and emission dispatch (CEED).

A novel algorithm termed Levy-based glowworm swarm optimization (LGSO) is proposed in this work, and it provides an excellent solution to the combined economic and emission dispatch (CEED) difficulties by specifying the generation of the optimal renewable energy systems (RES). Moreover, in hybrid renewable energy systems, the proposed scheme is extended by connecting the wind turbine because the thermal power plant could not control the aforementioned costs. In terms of economic cost, emission cost and transmission loss, the suggested CEED model outperforms other conventional schemes genetic algorithm, Grey wolf optimization, whale optimization algorithm (WOA), dragonfly algorithm (DA) and glowworm swarm optimization (GSO) and demonstrates its efficiency.

According to the results, the suggested model for Iteration 20 was outperformed GSO, DA and WOA by 23.46%, 97.33% and 93.33%, respectively. For Iteration 40, the proposed LGSO was 60%, 99.73% and 97.06% better than GSO, DA and WOA methods, respectively. The proposed model for Iteration 60 was 71.50% better than GSO, 96.56% better than DA and 95.25% better than WOA. As a result, the proposed LGSO was shown to be superior to other existing techniques with respect to the least cost and loss.

This research introduces the latest optimization algorithm known as LGSO to provide an excellent solution to the CEED difficulties by specifying the generation of the optimal RES. To the best of the authors’ knowledge, this is the first work that utilizes LGSO-based optimization for providing an excellent solution to the CEED difficulties by specifying the generation of the optimal RES.

In recent decades, the student population in dormitories has increased notably, primarily attributed to the growing number of international students. Dormitories serve as pivotal environments for student development. The coordination and compatibility among students can significantly influence their overall success. This study aims to introduce an innovative method for roommate selection and room allocation within dormitory settings.

In this study, initially, using multi-attribute decision-making methods including the Bayesian best-worst method and weighted aggregated sum product assessment, the incompatibility rate among pairs of students is calculated. Subsequently, using a linear mathematical model, roommates are selected and allocated to dormitory rooms pursuing the twin objectives of minimizing the total incompatibility rate and costs. Finally, the grasshopper optimization algorithm is applied to solve large-sized instances.

The results demonstrate the effectiveness of the proposed method in comparison to two common alternatives, i.e. random allocation and preference-based allocation. Moreover, the proposed method’s applicability extends beyond its current context, making it suitable for addressing various matching problems, including crew pairing and classmate pairing.

This novel method for roommate selection and room allocation enhances decision-making for optimal dormitory arrangements. Inspired by a real-world problem faced by the authors, this study strives to offer a robust solution to this problem.

This paper aims to model a technique that categorizes the texts from huge documents. The progression in internet technologies has raised the count of document accessibility, and thus the documents available online become countless. The text documents comprise of research article, journal papers, newspaper, technical reports and blogs. These large documents are useful and valuable for processing real-time applications. Also, these massive documents are used in several retrieval methods. Text classification plays a vital role in information retrieval technologies and is considered as an active field for processing massive applications. The aim of text classification is to categorize the large-sized documents into different categories on the basis of its contents. There exist numerous methods for performing text-related tasks such as profiling users, sentiment analysis and identification of spams, which is considered as a supervised learning issue and is addressed with text classifier.

At first, the input documents are pre-processed using the stop word removal and stemming technique such that the input is made effective and capable for feature extraction. In the feature extraction process, the features are extracted using the vector space model (VSM) and then, the feature selection is done for selecting the highly relevant features to perform text categorization. Once the features are selected, the text categorization is progressed using the deep belief network (DBN). The training of the DBN is performed using the proposed grasshopper crow optimization algorithm (GCOA) that is the integration of the grasshopper optimization algorithm (GOA) and Crow search algorithm (CSA). Moreover, the hybrid weight bounding model is devised using the proposed GCOA and range degree. Thus, the proposed GCOA + DBN is used for classifying the text documents.

The performance of the proposed technique is evaluated using accuracy, precision and recall is compared with existing techniques such as naive bayes, k-nearest neighbors, support vector machine and deep convolutional neural network (DCNN) and Stochastic Gradient-CAViaR + DCNN. Here, the proposed GCOA + DBN has improved performance with the values of 0.959, 0.959 and 0.96 for precision, recall and accuracy, respectively.

This paper proposes a technique that categorizes the texts from massive sized documents. From the findings, it can be shown that the proposed GCOA-based DBN effectively classifies the text documents.