Search results

Limitations encountered with the models developed in the previous studies had occurrences of global minima; due to which this study developed a new intelligent ubiquitous computational model that learns with gradient descent learning rule and operates with auto-encoders and decoders to attain better energy optimization. Ubiquitous machine learning computational model process performs training in a better way than regular supervised learning or unsupervised learning computational models with deep learning techniques, resulting in better learning and optimization for the considered problem domain of cloud-based internet-of-things (IOTs). This study aims to improve the network quality and improve the data accuracy rate during the network transmission process using the developed ubiquitous deep learning computational model.

In this research study, a novel intelligent ubiquitous machine learning computational model is designed and modelled to maintain the optimal energy level of cloud IOTs in sensor network domains. A new intelligent ubiquitous computational model that learns with gradient descent learning rule and operates with auto-encoders and decoders to attain better energy optimization is developed. A new unified deterministic sine-cosine algorithm has been developed in this study for parameter optimization of weight factors in the ubiquitous machine learning model.

The newly developed ubiquitous model is used for finding network energy and performing its optimization in the considered sensor network model. At the time of progressive simulation, residual energy, network overhead, end-to-end delay, network lifetime and a number of live nodes are evaluated. It is elucidated from the results attained, that the ubiquitous deep learning model resulted in better metrics based on its appropriate cluster selection and minimized route selection mechanism.

In this research study, a novel ubiquitous computing model derived from a new optimization algorithm called a unified deterministic sine-cosine algorithm and deep learning technique was derived and applied for maintaining the optimal energy level of cloud IOTs in sensor networks. The deterministic levy flight concept is applied for developing the new optimization technique and this tends to determine the parametric weight values for the deep learning model. The ubiquitous deep learning model is designed with auto-encoders and decoders and their corresponding layers weights are determined for optimal values with the optimization algorithm. The modelled ubiquitous deep learning approach was applied in this study to determine the network energy consumption rate and thereby optimize the energy level by increasing the lifetime of the sensor network model considered. For all the considered network metrics, the ubiquitous computing model has proved to be effective and versatile than previous approaches from early research studies.

The developed ubiquitous computing model with deep learning techniques can be applied for any type of cloud-assisted IOTs in respect of wireless sensor networks, ad hoc networks, radio access technology networks, heterogeneous networks, etc. Practically, the developed model facilitates computing the optimal energy level of the cloud IOTs for any considered network models and this helps in maintaining a better network lifetime and reducing the end-to-end delay of the networks.

The social implication of the proposed research study is that it helps in reducing energy consumption and increases the network lifetime of the cloud IOT based sensor network models. This approach helps the people in large to have a better transmission rate with minimized energy consumption and also reduces the delay in transmission.

In this research study, the network optimization of cloud-assisted IOTs of sensor network models is modelled and analysed using machine learning models as a kind of ubiquitous computing system. Ubiquitous computing models with machine learning techniques develop intelligent systems and enhances the users to make better and faster decisions. In the communication domain, the use of predictive and optimization models created with machine learning accelerates new ways to determine solutions to problems. Considering the importance of learning techniques, the ubiquitous computing model is designed based on a deep learning strategy and the learning mechanism adapts itself to attain a better network optimization model.

The loading and power variations in the power system, especially for the peak hours have abundant concussion on the loading patterns of the open access transmission system. During such unconditional state of loading the transmission line parameters and the line voltages show a substandard profile, which depicts exaction of congestion management of the power line in such events. The purpose of this paper is to present an uncomplicated and economical model for congestion management using flexible AC transmission system (FACTS) devices.

The approach desires a two-step procedure, first by optimal placement of thyristor controlled series capacitor (TCSC) and static VAR compensator (SVC) as FACTS devices in the network; second tuning the control parameters to their optimized values. The optimal location and tuning of TCSC and SVC represents a hectic optimization problem, due to its multi-objective and constrained nature. Hence, a reassuring heuristic optimization algorithm inspired by behavior of cat and firefly is employed to find the optimal placement and tuning of TCSC and SVC.

The effectiveness of the proposed model is tested through simulation on standard IEEE 14-bus system. The proposed approach proves to be better than the earlier existing approaches in the literature.

With the completed simulation and results, it is proved that the proposed scheme has reduced the congestion in line, thereby increasing the voltage stability along with improved loading capability for the congested lines.

The usefulness of the proposed scheme is justified with the computed results, giving convenience for implementation to any practical transmission network.

This paper fulfills an identified need to study exaction of congestion management of the power line.

The purpose of this study is to alleviate the specified issues to a great extent. To promote patients’ health via early prediction of diseases, knowledge extraction using data mining approaches shows an integral part of e-health system. However, medical databases are highly imbalanced, voluminous, conflicting and complex in nature, and these can lead to erroneous diagnosis of diseases (i.e. detecting class-values of diseases). In literature, numerous standard disease decision support system (DDSS) have been proposed, but most of them are disease specific. Also, they usually suffer from several drawbacks like lack of understandability, incapability of operating rare cases, inefficiency in making quick and correct decision, etc.

Addressing the limitations of the existing systems, the present research introduces a two-step framework for designing a DDSS, in which the first step (data-level optimization) deals in identifying an optimal data-partition (Popt) for each disease data set and then the best training set for Popt in parallel manner. On the other hand, the second step explores a generic predictive model (integrating C4.5 and PRISM learners) over the discovered information for effective diagnosis of disease. The designed model is a generic one (i.e. not disease specific).

The empirical results (in terms of top three measures, namely, accuracy, true positive rate and false positive rate) obtained over 14 benchmark medical data sets (collected from https://archive.ics.uci.edu/ml) demonstrate that the hybrid model outperforms the base learners in almost all cases for initial diagnosis of the diseases. After all, the proposed DDSS may work as an e-doctor to detect diseases.

The model designed in this study is original, and the necessary parallelized methods are implemented in C on Cluster HPC machine (FUJITSU) with total 256 cores (under one Master node).

The primary aim of this study is to detail the use of soft computing techniques in business and management research. Its objectives are as follows: to conduct a comprehensive scientometric analysis of publications in the field of soft computing, to explore the evolution of keywords, to identify key research themes and latent topics and to map the intellectual structure of soft computing in the business literature.

This research offers a comprehensive overview of the field by synthesising 43 years (1980–2022) of soft computing research from the Scopus database. It employs descriptive analysis, topic modelling (TM) and scientometric analysis.

This study's co-citation analysis identifies three primary categories of research in the field: the components, the techniques and the benefits of soft computing. Additionally, this study identifies 16 key study themes in the soft computing literature using TM, including decision-making under uncertainty, multi-criteria decision-making (MCDM), the application of deep learning in object detection and fault diagnosis, circular economy and sustainable development and a few others.

This analysis offers a valuable understanding of soft computing for researchers and industry experts and highlights potential areas for future research.

This study uses scientific mapping and performance indicators to analyse a large corpus of 4,512 articles in the field of soft computing. It makes significant contributions to the intellectual and conceptual framework of soft computing research by providing a comprehensive overview of the literature on soft computing literature covering a period of four decades and identifying significant trends and topics to direct future research.

This paper aims to propose a novel methodology for optimal voltage source converter (VSC) station installation in hybrid alternating current (AC)/direct current (DC) transmission networks.

In this analysis, a unified power flow model has been developed for the optimal power flow (OPF) problem for VSC-based high voltage direct current (VSC-HVDC) transmission network and solved using a particle swarm optimization (PSO) algorithm. The impact of the HVDC converter under abnormal conditions considering N-1 line outage contingency is analyzed against the congestion relief of the overall transmission network. The average loadability index is used as a severity indicator and minimized along with overall transmission line losses by replacing each AC line with an HVDC line independently.

The developed unified OPF (UOPF) model converged successfully with (PSO) algorithm. The OPF problem has satisfied the defined operational constraints of the power system, and comparative results are obtained for objective function with different HVDC test configurations represented in the paper. In addition, the impact of VSC converter location is determined on objective function value.

A novel methodology has been developed for the optimal installation of the converter station for the point-to-point configuration of HVDC transmission. The developed unified OPF model and methodology for selecting the AC bus for converter installation has effectively reduced congestion in transmission lines under single line outage contingency.

In this work, the design problem of hydrodynamic plain journal bearings is formulated as a multi-objective optimization problem to improve bearing performance under different operating conditions.

The problem is solved using a hybrid approach combining genetic algorithm and sequential quadratic programming. The selected state variables are oil leakage flow rate, power loss and minimum oil film thickness. The selected design variables are the radial clearance, length-to-diameter ratio, oil viscosity, oil supply pressure and oil supply groove angular position. A validated empirical model is adopted to provide relatively accurate estimation of the bearing state variables with reduced computations. Pareto optimal solution sets are obtained for different operating conditions, and secondary selection criteria are proposed to choose a final optimum design.

The adopted hybrid optimization approach is a random search algorithm that generates a different solution set for each run, thus a different bearing design. For a number of runs, it is found that the key design variables that significantly affect the optimum state variables are the bearing radial clearance, oil viscosity and oil supply pressure. Additionally, oil viscosity is found to represent the significant factor that distinguishes the optimum designs obtained using the implemented secondary selection criteria. Finally, the results of the proposed optimum design framework at different operating conditions are presented and compared.

The proposed multi-objective formulation of the bearing design problem can provide engineers with a systematic approach and an important degree of flexibility to choose the optimum design that best fits the application requirements.

Aircraft pitch control is fundamental for the performance of micro aerial vehicles (MAVs). The purpose of this paper is to establish a simple experimental procedure to calibrate pitch instrumentation and classical control algorithms. This includes developing an efficient pitch angle observer with optimal estimation and evaluating controllers under uncertainty and external disturbances.

A wind tunnel test bench is designed to simulate fixed-wing aircraft dynamics. Key elements of the instrumentation commonly found in MAVs are characterized in a gyroscopic test bench. A data fusion algorithm is calibrated to match the gyroscopic test bench measurements and is then integrated into the autopilot platform. The elevator-angle to pitch-angle dynamic model is obtained experimentally. Two different control algorithms, based on model-free and model-based approaches, are designed. These controllers are analyzed in terms of parametric uncertainties due to wind speed variations and external perturbation because of sudden weight distribution changes. A series of experimental tests is performed in wind-tunnel facilities to highlight the main features of each control approach.

With regard to the instrumentation algorithms, a simple experimental methodology for the design of optimal pitch angle observer is presented and validated experimentally. In the context of the platform design and identification, the similitude among the theoretical and experimental responses shows that the platform is suitable for typical pitch control assessment. The wind tunnel experiments show that a fixed linear controller, designed using classical frequency domain concepts, is able to provide adequate responses in scenarios that approximate the operation of MAVs.

The aircraft orientation observer can be used for both pitch and roll angles. However, for simultaneousyaw angle estimation the proposed design method requires further research. The model analysis considers a wind speed range of 6-18 m/s, with a nominal operation of 12 m/s. The maximum experimentally tested reference for the pitch angle controller was 20°. Further operating conditions may require more complex control approaches (e.g. scheduling, non-linear, etc.). However, this operating range is enough for typical MAV missions.

The study shows the design of an effective pitch angle observer, based on a simple experimental approach, which achieved locally optimum estimates at the test conditions. Additionally, the instrumentation and design of a test bench for typical pitch control assessment in wind tunnel facilities is presented. Finally, the study presents the development of a simple controller that provides adequate responses in scenarios that approximate the operation of MAVs, including perturbations that resemble package delivery and parametric uncertainty due to wind speed variations.

This paper aims to present the design optimisation using genetic algorithm (GA) to achieve the highest strength to weight (S/W) ratio, for cold-formed steel residential roof truss.

The GA developed in this research simultaneously optimises roof pitch, truss configurations, joint coordinates and applied loading of typical dual-pitched symmetrical residential roof truss. The residential roof truss was considered with incremental uniform distributed loading, in both gravitational and uplift directions. The structural analyses of trusses were executed in this GA using finite element toolbox. The ultimate strength and serviceability of trusses were checked through the design formulation implemented in GA, according to the Australian standard, AS/NZS 4600 Cold-formed Steel Structures.

An optimum double-Fink roof truss which possess highest S/W ratio using GA was determined, with optimum roof pitch of 15°. The optimised roof truss is suitable for industrial application with its higher S/W ratio and cost-effectiveness. The combined methodology of multi-level optimisation and simultaneous optimisation developed in this research could determine optimum roof truss with consistent S/W ratio, although with huge GA search space.

The sizing of roof truss member is not optimised in this paper. Only single type of cold-formed steel section is used throughout the whole optimisation. The design of truss connection is not considered in this paper. The corresponding connection costs are not included in the proposed optimisation.

The optimum roof truss presented in this paper is suitable for industrial application with higher S/W ratio and lower cost, in either gravitational or uplift loading configurations.

This research demonstrates the approaches in combining multi-level optimisation and simultaneous optimisation to handle large number of variables and hence executed an efficient design optimisation. The GA designed in this research determines the optimum residential roof truss with highest S/W ratio, instead of lightest truss weight in previous studies.

The paper aims to present an application of teaching learning-based optimization (TLBO) algorithm and static Var compensator (SVC) to improve the steady state and dynamic performance of self-excited induction generators (SEIG).

The TLBO algorithm is applied to generate the optimal capacitance to maintain rated voltage with different types of prime mover. For a constant speed prime mover, the TLBO algorithm attains the optimal capacitance to have rated load voltage at different loading conditions. In the case of variable speed prime mover, the TLBO methodology is used to obtain the optimal capacitance and prime mover speed to have rated load voltage and frequency. The SVC of fixed capacitor and controlled reactor is used to have a fine tune in capacitance value and control the reactive power. The parameters of SVC are obtained using the TLBO algorithm.

The whole system of three-phase induction generator and SVC are established under MatLab/Simulink environment. The performance of the SEIG is demonstrated on two different ratings (i.e. 7.5 kW and 1.5 kW) using the TLBO algorithm and SVC. An experimental setup is built-up using a 1.5 kW three-phase induction machine to confirm the theoretical analysis. The TLBO results are matched with other meta heuristic optimization techniques.

The paper presents an application of the meta-heuristic algorithms and SVC to analysis the steady state and dynamic performance of SEIG with optimal performance.

This study aims to investigate the possible use of a deep neural network (DNN) as an inverse solver.

Different models based on DNNs are designed and proposed for the resolution of inverse electromagnetic problems either as fast solvers for the direct problem or as straightforward inverse problem solvers, with reference to the TEAM 25 benchmark problem for the sake of exemplification.

Using DNNs as straightforward inverse problem solvers has relevant advantages in terms of promptness but requires a careful treatment of the underlying problem ill-posedness.

This work is one of the first attempts to exploit DNNs for inverse problem resolution in low-frequency electromagnetism. Results on the TEAM 25 test problem show the potential effectiveness of the approach but also highlight the need for a careful choice of the training data set.