Low Computational Time Research Articles

Self-Attention conditional generative adversarial network optimised with crayfish optimization algorithm for improving cyber security in cloud computing

The decentralized and distributed architecture of cloud computing promotes adoption and growth in various societal domains, including education, government, information technology, business, entertainment. Cloud computing (CC) makes a broad range of information technologies available. Security and privacy are key challenges in storing big data in the cloud. To overcome this challenge, a Self-Attention Conditional Generative Adversarial Network Optimised with Crayfish Optimization Algorithm for Improving Cyber Security in Cloud Computing (CybS-CC-SACGANCOA) is proposed in this paper to enhance the safety of CC environment. The input data is amassed from NSL-KDD database. After that, the data is fed to pre-processing segment. The segment of pre-processing eliminates Cloud data termination and missing value replacement using Reformed Phase Conserving Vibrant Range Compression filter. The results of pre-processing serves for feature selection. The optimal features are selected by means of Manta Ray Foraging Optimization Algorithm (MRFOA). Cloud data is categorized as normal and abnormal data, like Denial-of-Service (DoS), Probe, Remote to local attack (R2L), User to root attack (U2R) by the help of SACGAN. Crayfish Optimization Algorithm (COA) is proposed to optimize the SACGAN classifier that classifies anomaly data precisely. The proposed CSCC-SACGANCOA technique is activated in Python under some metrics. The proposed CSCC-SACGANCOA approach has attained higher detection accuracy, lower computation time, higher AUC, higher scalability and lower detection error rate compared to the existing methods.

Accuracy and temporal analysis of non-Newtonian models of blood in the computational FFR – Numerical implementation

Non-invasive assessment of stenosed coronary is a goal for clinical applications. Thus, engineering aligned with medicine has been the solution to solve this problem. This work, serving as a proof of concept, has the main goal to predict the non-invasive fractional flow reserve (FFR) in an atherosclerotic coronary artery. A 3-element Windkessel and Womersley models were used to model boundary conditions of the patient-specific coronary arteries: the pressure at the outlets of the artery and the velocity at the inlet, respectively. Apart from implementing the previous conditions in the numerical code, the novelty of this work is to implement and use, in numerical simulations, Newtonian and non-Newtonian models for blood such as Carreau, Carreau-Yasuda, Casson and Simplified Phan-Thien/Tanner to analyse the accuracy of the computed FFR and the computational time of the simulations. Results indicate that the non-Newtonian viscoelastic model, Simplified Phan-Thien/Tanner, took the longest time but produced the most accurate results - 8h and 2.7% relative error between invasive and non-invasive FFR. The shear-thinning non-Newtonian models required lower computational times but returned a higher average error (3.9h; 7.6% error) which is considered significant. The Newtonian model required the least time but had the highest error value (2.9h; 7.8% error). Thus, although the computational time considering the non-Newtonian viscoelastic model is the highest, this model must be considered in the numerical simulations to obtain the FFR since it is the most accurate for this patient case. This research is a step forward to numerically quantify the non-invasive FFR of a patient.

Online algorithms for ambulance routing in disaster response with time-varying victim conditions

We present a novel online optimization approach to tackle the ambulance routing problem on a road network, specifically designed to handle uncertainties in travel times, triage levels, required treatment times of victims, and potential changes in victim conditions in post-disaster scenarios. We assume that this information can be learned incrementally online while the ambulances get to the scene. We analyze this problem using the competitive ratio criterion and demonstrate that, when faced with a worst-case instance of this problem, neither deterministic nor randomized online solutions can attain a finite competitive ratio. Subsequently, we present a variety of innovative online heuristics to address this problem which can operate with very low computational running times. We assess the effectiveness of our online solutions by comparing them with each other and with offline solutions derived from complete information. Our analysis involves examining instances from existing literature as well as newly generated large-sized instances. One of our algorithms demonstrates superior performance when compared to the others, achieving experimental competitive ratios that closely approach the optimal ratio of one.

3-D Passive Cavitation Imaging Using Adaptive Beamforming and Matrix Array Transducer With Random Apodization.

With the development of promising cavitation-based treatments, the interest in cavitation monitoring with passive acoustic mapping (PAM) is significantly increasing. While most of studies regarding PAM are performed in 2-D, 3-D imaging modalities are getting more attention relying on either custom-made or commercial matrix probes. Unless specific phased-arrays are used for a specific application, limitations due to probe apertures often results in poor performances of the 3-D mapping, due to the use of a delay-and-sum (DAS) classic beamformer, which results in strong artifacts and large main lobe sizes. In this article, 3D-PAM is achieved by performing adaptive beamforming in the frequency domain (FD) in 3-D, and using a random sparse apodization of a commercial matrix array driving only 256 elements among the 1024 available. It reduces the computation time and makes use of only one 256-channel research platform. Three beamformers have been implemented in 3-D and in the FD: the DAS beamformer, which corresponds to the beamformer used in previous 3D-PAM studies, the robust capon beamformer (RCB), an adaptive algorithm widely used in 2D-PAM for its high performances, and the MidWay (MW) beamformer, an adaptive algorithm with a computation complexity equivalent to the one of DAS. These algorithms are evaluated both in simulations and experiments with a harmonic source at different positions, and are also applied to real cavitation signals. The results show that, in the case of matrix arrays of small aperture such as generic commercial matrix probes, the DAS beamformer leads to large main lobe sizes, while adaptive beamformers largely improve the performances of the mapping. The low computation time and its parameter-free character make MW beamformer a good compromise for 3D-PAM applications. It thus appears that a random sparse apodization combined with adaptive beamforming is a good solution to achieve high-performance 3D-PAM with manageable devices.

A surrogate-based heuristic for production planning problem of orders in small foundries

Market foundry production processes are characterized by raw materials that feed a furnace that produces metal alloys with limited capacity to meet item order demand. The foundry production system considered here is make-to-order. Although in the literature, production planning does not usually consider items produced as belonging to orders, it is essential to address this specificity. All component items must be produced to fulfill an order. We propose a surrogate-based heuristic (SUBH) to address the production planning problem of orders in small foundries. The quality of the lower bounds is compared to that of the linearly relaxed problem. The feasibility and optimality of the solutions are tested. Most tested instances are proved optimal. For infeasible solutions, we proposed a feasibility procedure based on item weight and order costs. We obtain excellent results with low computational time.

An internet of health things-driven skin cancer classification using progressive cyclical convolutional neural network with ResNexT50 optimized by exponential particle swarm optimization

Skin cancer has become more common in the last few decades according to reports by the World Health Organization. Currently, 1,32,000 melanoma skin cancer cases and around three million non-melanoma cases are reported annually worldwide. Early skin cancer identification with classification allows for effective diagnosis and therapy for patients. Therefore, an internet of health things-driven deep learning approach for identification with classification of skin cancer based on Progressive Cyclical Convolutional Neural Network with ResNexT50 transfer learning optimized by Exponential Particle Swarm Optimization (IoHT-SC-PCCNN-RNT-EXPSO) is proposed in this manuscript. Here, the input skin cancer images are amassed from international Skin Imaging Collaboration (ISIC) image archive dataset. The Dynamic Temporal Filter (DTF) is used for removing the noise, and also enhances the skin cancer images quality. In which, PCCNN does not adopt any optimization methods for determining the optimum parameter to offer accurate skin cancer classification. So, Exponential Particle Swarm Optimization (EXPSO) is proposed for optimizing PCCNN to help it precisely classify the skin cancer. The proposed IoHT-SC-PCCNN-RNT-EXPSO method is implemented in MATLAB. The metrics, like accuracy, recall, precision, f1-Score, specificity, computation time, error rate are evaluated to evaluate the effectiveness of the proposed technique. The proposed MSCC-DI-SDRN-JSOA demonstrated improved specificity with percentages of 27.35 %, 28.64 %, and 24.38 %. Additionally, it showed lower computation time by 37.28 %, 29.39 %, and 28.44 %, and higher accuracy by 30.50 %, 32.39 %, and 31.54 % compared to the existing methods, like IoHT-SC-CNN, IoHT-SC-KNN and IoHT-SC-DWNN-EPO respectively.

Health Monitoring in IoT with Context-Aware Deep Convolutional Spiking Neural Network and Woodpecker Mating Algorithm

In recent years, many context-sensitive approaches have been established to offer physiological information about the wellness of each person. While the patient’s health is being monitored, there are delays in the cloud data transfer. To overcome these delays, a Deep Convolutional Spike Neural Network (DCSNN) with a Woodpecker Mating Algorithm (WMA) is proposed in this manuscript for monitoring the healthcare data in the Internet of Things (IoT)-based context-aware architecture (DCSNN-WMA-HCM-IoT-CAA). Here, the input data are amassed from real-time datasets. Then the data are supplied to the pre-processing. The pre-processing data involve the assortment phase, data storage phase, and data redundancy phase. In the redundancy phase, the Kernel co-relation method is employed to remove the repeated data. The pre-processing output is given to the feature extraction. The feature is extracted under the fast discrete Curvelet transform method. After that, the extracted features are given to DCSNN optimized with WMA to classify regular, irregular, and critical conditions of the patient. The proposed DCSNN-WMA-HCM-IoT-CAA method is activated in OMNeT++. The proposed DCSNN-WMA-HCM-IoT-CAA approach attains 4.08%, 8.17%, 9.32%, and 5.17% high accuracy, 14.3%, 15.4%, 19.51%, and 27.81% lower computation Time and 12.29%, 15.36%, 11.55%, and 13.91% higher AUC compared with existing methods.

Control of Distributed Converter-Based Resources in a Zero-Inertia Microgrid Using Robust Deep Learning Neural Network

Considering the evolution of future microgrids (MGs) towards zero-inertia level due to the penetrations of distributed converter-based resources (DCRs), a large number of data produced by these generations will lead the control decisions to be more complicated than conventional power systems. This paper presents a control strategy for a zero-inertia MG with DCRs using a robust deep learning neural network (RDeNN). In a training phase, a sub-space state-based identification method is employed to monitor and analyze the data regarding stability indices, i.e., damping and frequency of dominant modes, and robustness against uncertainties. In addition, a mixed H2/H∞ control strategy is applied to enhance the training efficacy in the frequency and voltage control loops of DCRs. The trained RDeNN is activated to make quick and effective control decisions by using only measured signals from the MG. Simulation results are verified in the zero-inertia MG (or the grid with 100% DCRs) and compared with several existing control techniques. The study results demonstrate the advantages of the proposed RDeNN in many aspects such as low computational time, require-less physical controller models, fast and flexible stabilizing responses, and high robustness against various time delays, data quality issues, and MG uncertainties.

Using a Minimalist Bi-LSTM for Multi-Faceted Bearing Fault Detection

A bidirectional long short-term memory (Bi-LSTM) model is developed to predict a multi-faceted bearing health characteristic using time series vibration measurements from the Case Western Reserve University (CWRU) seeded fault test data. A maximal amount of data is applied with minimal preprocessing to test the model’s capabilities and several hyperparameters are tuned to maximize model performance. The utility of the CWRU dataset for related problems and the applicability of Bi-LSTM architecture for time series data is highlighted. The proposed model achieved a final test prediction accuracy of 98.42% and had low computation time, making it an interesting candidate for application in bearing fault prognosis.

Evaluating procedures in the NEH heuristic for the PFSP - SIST

The development and assessment of 48 heuristics for the sequence-independent setup time permutation flow shop problem (PFSP-SIST) are presented in this article. This contribution combines four tie-breaking solutions with twelve priority rules for the NEH heuristic fourth and first stage, respectively. Heuristics are evaluated on Ruiz and Allahverdi (2007) benchmark problem instances, that covers small, medium and large-size problems. The popular accelerations of Taillard were used in all tests, which were adapted to the sequence-independent setup time constraint. The aim is to reduce the longest job completion time, which is also referred to as makespan. Computation results show that using different tie-breaking strategies has a greater impact on performance than using different priority rules. The heuristics that presented the best results in relatively low computation time are those that use the FFs tie-breaking strategy procedure to the sequence-independent setup time problem.

Visibility Evaluation in Microfacet Theory.

Reflectance models capture many types of visual appearances. The most plausible reflectance models follow the Microfacet theory, which is specifically based on statistical representations, with an analytic visibility term. This visibility term has a significant impact on appearance. Visibility computed with the masking term proposed by Smith[1], and revisited by Ashikhmin et al.[2], is nowadays considered as the most plausible in the literature. It is simple and efficient to evaluate for statistical distributions, but it relies on assumptions that are not necessarily respected by real surfaces. This paper proposes an in-depth study of masking for meshed height-field surfaces, generated either from measured real-world materials or from functions derived from distributions of surface normals. We experimentally estimate the masking (and shadowing) of surfaces using a ray-casting technique, and compare their measurements with the theoretical model from Smith and Ashikhmin et al. We show that their assumptions are too restrictive for a majority of real-world surfaces. We propose a model capable of predicting how close the theoretical masking term can be from the masking term estimated by a ray-casting approach. Although most surfaces break their assumptions, our results show that the term from Smith and Ashikhmin et al. can still be reasonably employed for a fraction in a set of more than 400 measured surfaces, with low errors compared to a ray-casting masking estimation, much lower computation times, and very similar visual appearances. Our model can be used to predict the incurred error on a physically-based rendering simulation with a microfacet-based BRDF created from real-world surfaces, instead of explicitly calculating the masking term from its height field.

Coupling the COST reference plasma jet to a microfluidic device: a computational study

The use of microfluidic devices in the field of plasma-liquid interaction can unlock unique possibilities to investigate the effects of plasma-generated reactive species for environmental and biomedical applications. So far, very little simulation work has been performed on microfluidic devices in contact with a plasma source. We report on the modelling and computational simulation of physical and chemical processes taking place in a novel plasma-microfluidic platform. The main production and transport pathways of reactive species both in plasma and liquid are modelled by a novel modelling approach that combines 0D chemical kinetics and 2D transport mechanisms. This combined approach, applicable to systems where the transport of chemical species occurs in unidirectional flows at high Péclet numbers, decreases calculation times considerably compared to regular 2D simulations. It takes advantage of the low computational time of the 0D reaction models while providing spatial information through multiple plug-flow simulations to yield a quasi-2D model. The gas and liquid flow profiles are simulated entirely in 2D, together with the chemical reactions and transport of key chemical species. The model correctly predicts increased transport of hydrogen peroxide into the liquid when the microfluidic opening is placed inside the plasma effluent region, as opposed to inside the plasma region itself. Furthermore, the modelled hydrogen peroxide production and transport in the microfluidic liquid differs by less than 50% compared with experimental results. To explain this discrepancy, the limits of the 0D–2D combined approach are discussed.

MPTree: A Sampling-based Vehicle Motion Planner for Real-time Obstacle Avoidance

This paper presents a novel and modular framework, named MPTree, for real-time vehicle motion planning with dynamic obstacle avoidance. MPTree adopts a sampling-based algorithm, to explore a tree of Motion Primitives (MPs) and return near-optimal trajectories. Specifically, MPTree builds motion primitives to connect the tree nodes (waypoints), sampled in a mesh of waylines on the local planning horizon. The tree exploration is based on a semi-structured RRTa, with an application-specific cost function (e.g., minimum-jerk or minimum-time) and high-level behavioral policy. We show examples of MPTREE’s specialization for urban environments and autonomous racing, using fast-to-evaluate motion primitives to accelerate the tree exploration phase. A prototype implementation is tested in a closed-loop simulation environment. Our preliminary results show that MPTree provides feasible collision-free trajectories while ensuring low computational times.

PID algorithm based on GPC for second-order models with input and output constraints

This paper presents a novel constrained PID algorithm that performs almost the same as a constrained GPC tuned with a unit control horizon and an output soft constraint. The proposed approach computes the PID tuning parameters using the unconstrained GPC solution for first or second-order process models and uses a geometric approach, which avoids the use of an optimiser, to compute the final control action combining the PID tuning with a constraint-mapping law. Simulation results are used to illustrate the simplicity and good performance that can be obtained with the proposed approach, which is an interesting solution for PID applications in which output constraints are considered and low computation time of the control law is required.

Super-Rays Grouping Scheme and Novel Coding Architecture for Computational Time Reduction of Graph-Based Light Field Coding

Graph-based Light Field coding using the concept of super-rays is powerful to exploit signal redundancy along irregular shapes and achieves good energy compaction, compared to rectangular block -based approaches. However, its main limitation lies in the high time complexity for eigen-decomposition of each super-ray local graph, a high number of which can be found in a Light Field when segmented into super-rays. This paper examines a grouping scheme for super-rays in order to reduce the number of eigen-decomposition times, and proposes a novel coding architecture to handle the signal residual data arising for each super-ray group, as a tradeoff to achieve lower computational time. Experimental results have shown to reduce a considerable amount of decoding time for Light Field scenes, despite having a slight increase in the coding bitrates when compared with the original non-grouping super-ray-based approach. The proposal also remains to have competitive performance in Rate Distortion in comparison to HEVC-based and JPEG Pleno -based methods.

Binarized Spiking Neural Network with blockchain based intrusion detection framework for enhancing privacy and security in cloud computing environment

Cloud computing (CC) is prone to attacks, which upsurges complication and erudition. By this, its origins provocative implications can enterprise data veracity, concealment, and accessibility. To overwhelm these issues, a Binarized Spiking Neural Network with block chain based deputized proof of stake consensus (DPoS) algorithm fostered intrusion detection scheme is proposed in this manuscript to enhance the privacy and the security on the cloud computing Environment (EP-DPoSBC-ES-BS4NN-IDS-CC). The data is amassed from NSL-KDD benchmark dataset. The first-level privacy process is carried with block chain based deputized proof of stake consensus (DPoS) algorithm. The secondary level privacy process is carried out by utilizing the pre-processing and the feature selection process. For, pre-processing, proposed Basic interlude gradient filtering (BIGF) are utilized to eradicate the unsolicited content and filtering pertinent data. The pre-processing outcome is supplied to the feature selection phase. Here, the ideal features are taken with the help of Weightiness espoused feature assortment approaches (WEFA). The data is classified as normal or abnormal based on Binarized Spiking Neural Network. Subsequently, the proposed EP-DPoSBC-ES-BS4NN-IDS-CC is examined under some performance metrics. The proposed technique attains 12.94 %, 17.68 %, 17.99 % and 13.96 % improved accuracy; 59.9 %, 50 %, 31.45 % and 48.17 % lower Computation Time and 3.19 %, 0.83 %, 2.1 % and 5.43 % higher AUC than the existing methods. Customers and cloud service providers may find this framework useful as a decision-support tool in helping them move their data in a safe, timely, and reliable manner. In future work, a prototype of the approach will develop in real-world scenario, capably inside a tight network of connected computers. It allows evaluate effectively in real-world utility.

Iterative On Surface Radiation Conditions for fast and reliable single and multiple scattering analyses of arbitrarily shaped obstacles

In this paper we develop an iterative method to perform single and multiple scattering analyses of both convex and non-convex scatterers at very low computational cost and time. The computational method proposed will resolve the current inaccuracy of the On Surface Radiation Conditions (OSRC) in estimating the scattered field from non-convex obstacles and allows a fast and reliable single- and multiple-scattering analyses in reduced spatial dimensions. We demonstrate the reliability and efficiency of the proposed method in solving two- and three-dimensional time-harmonic acoustic scattering problems. Non-Uniform Rational B-Splines were used to represent the obstacle boundaries providing a seamless connection to geometrical representation. The proposed Iterative On Surface Radiation Conditions (ITOSRC) method tremendously reduces the meshing and analysis time and paves the way for shape and topology optimization of future devices relying on wave prpagation phenomena.

The dynamic behaviour of ORC-based power units fed by exhaust gases of internal combustion engines in mobile applications

Exhaust gases Waste Heat Recovery (WHR) in Internal Combustion Engines (ICEs) performed through ORC-based Power Units (ORC-bPU) ensures a reduction of fuel consumption and consequently CO2 emissions. Nevertheless, high fluctuations of hot source push the ORC-bPU to work frequently in severe off-design conditions. Hence, a deep knowledge of the unit dynamic behaviour is fundamental to develop control and operating strategies allowing to achieve a successful recovery. Dynamic response assessment of ORC-bPUs has been treated in literature but making mainly reference to theoretical approaches or to variations of input variables without considering the matching to the engine and the necessary constraints which are present in a real mobile application. Moreover, Moving Boundary (MB) models are generally used as theoretical tools to support the dynamic analysis focusing the attention on Heat Recovery Vapor Generator (HRVG) which rules the plant dynamic response. In MB models, boundary conditions at the HRVG exit are mainly fixed by the expander and by the remaining circuit. To date, the attention was focused on the presence as expander of dynamic machines (turbine), deserving an evident lower attention to volumetric expanders nonetheless their higher suitability for low-medium scale ORC applications (few kWs). To fill these knowledge gaps, a novel approach is pursued in the present paper. The dynamic response of an ORC-bPU was experimentally observed for a step change of torque and revolution speed of an ICE directly connected to the recovery unit. The variation of engine operating conditions produced an unsteady variation of the temperature and flow rate of the exhaust gas feeding the unit. The dynamics of the engine and the connecting pipes is considered as well as all the typical constraints of a real situation. Results show HRVG and exhaust pipe ruling the dynamic behaviour of the unit, leading to long time constant and raising time of gas temperature of 150 s and 300 s respectively. These results show that the unit almost always works in transient conditions being engine torque and speed variations very fast. Nevertheless, thanks to the self-regulation capacity and the robustness of the scroll expander, the unit reacts in a satisfactory way. A further novelty of the present study concerns the integration of the widely used Moving Boundary (MB) approach with Permeability theory which considers the presence of a volumetric expander and all the ither downstream components, finding a match not available in literature between the HRVG and a volumetric expander and pump. The results of the new Permeability-Moving Boundary model (P-MB) was compared with those of a more comprehensive mathematical model. The comparisons show a comparable accuracy and a significantly lower computational time achieved with P-MB. Hence, P-MB could be implemented on board to set up control strategies enhancing the recovery tuned by a model-based approach.

Situation identification in smart wearable computing systems based on machine learning and Context Space Theory

Wearable devices and smart sensors are increasingly adopted to monitor the behaviors of human and artificial agents. Many applications rely on the capability of such devices to recognize daily life activities performed by the monitored users in order to tailor their behaviors with respect to the occurring situations. Despite the constant evolution of smart sensing technologies and the numerous research in this field, an accurate recognition of in-the-wild situations still represents an open research challenge. This work proposes a novel approach for situation identification capable of recognizing the activities and the situations in which they occur in different environments and behavioral contexts, processing data acquired by wearable and environmental sensors.An architecture of a situation-aware wearable computing system is proposed, inspired by Endsley’s situation-awareness model, consisting of a two-step approach for situation identification. The approach first identifies the daily life activities via a learning-based technique. Simultaneously, the context in which the activities are performed is recognized using Context Space Theory. Finally, the fusion between the context state and the activities allows identifying the complex situations in which the user is acting. The knowledge regarding the situations forms the basis on which novel and smarter applications can be realized.The approach has been evaluated on the ExtraSensory public dataset and compared with state-of-the-art techniques, achieving an accuracy of 96% for the recognition of situations and with significantly low computational time, demonstrating the efficacy of the two-step situation identification approach.

Klasifikacija vrsta drva prema slikama uz pomoć dvodimenzionalne konvolucijske neuronske mreže

The woodworking industry’s recognition and classification of timber is essential for trade, production and timber science. Traditional methods of identifying wood types are complex, time-consuming, costly and require expertise in wood science. Traditional techniques have been replaced by convolutional neural networks (CNNs), a deep learning tool to better identify wood species. In contrast to earlier studies that used pretrained models, a novel architecture designed explicitly for the WOOD-AUTH dataset was proposed in this study to develop a new 2D CNN model. The data collection encompasses high-level visual representations of 12 distinct types of timber. It is aimed to create a simpler and faster model as an alternative to time-consuming and heavy wood classification models. Compared to previous studies, this research worked with a newly structured 2D CNN network based on 12 wood species. High accuracy and fast computation time were achieved using fewer numbers (three layers) of the convolutional neural network. The proposed model achieved 94 % accuracy, 87 % precision, 81 % recall, 80 % F1 score and 112 minutes 27 seconds computation time. The 2D CNN model performed better than the transfer learning models regarding training epochs. The primary benefit of the model is its ability to achieve high accuracy with lower computation time, even at high epochs compared to other models. The introduced 2D CNN model produced satisfactory outcomes for wood species classification.