Average Computation Time Research Articles

Investigation of Gaussian mixture clustering model for online diagnosis of tip-wear in nanomachining

This paper studied an unsupervised machine learning method to achieve real-time diagnosis of tip wear in tip-based nanomachining with an Atomic Force Microscope (AFM). The unsupervised Gaussian Mixture Model (GMM) was applied for online pattern recognition using the collected process data. In this work, the time varying signal of machining force was collected and managed in the form of moving data windows. The characteristics of the nanomachining force signal, including the maximum force, peak to peak force, and the variance, were calculated as the data of extracted features to indicate the tip wear conditions. Outliers were identified and removed using the Mahalanobis Distance Detection. A GMM model was trained using the historical processing data, in which the tip wear states were identified by clustering the feature parameters of each data frame. The change of the tip conditions was detected and tracked through the changing numbers of the tip failure points in the data windows. Experiment results showed that the highest and the average recognition accuracy of the proposed model was 1 and 0.8367 with the longest and the average calculation time of 0.031 s and 0.025 s. Compared with supervised and semi-supervised machine learning algorithms, the GMM based on unsupervised machine learning model has slightly lower recognition accuracy, but much shorter calculation time, which is suitable for online automatic diagnosis of tool wear in large-scale nanomanufacturing in real time.

Automation of Property Acquisition of Single Track Depositions Manufactured through Direct Energy Deposition

Metallic additive manufacturing processes have been significantly developed since their inception with modern systems capable of manufacturing components for structural applications. However, successful processing through these methods requires extensive experimentation before optimised parameters can be found. In laser-based processes, such as direct energy deposition, it is common for single track beads to be deposited and subjected to analysis, yielding information on how the input parameters influence characteristics such as the output’s adhesion to the substrate. These characteristics are often determined using specialised software, from images obtained by cross-section cutting the line beads. The proposed approach was based on a Python algorithm, using the scikit-image library and optical microscopy imaging from produced 18Ni300 Maraging steel on H13 tool steel, and it computes the relevant properties of DED-produced line beads, such as the track height, width, penetration, wettability angles, cross-section areas above and below the substrate and dilution proportion. 18Ni300 Maraging steel depositions were optimised with a laser power of 1550 W, feeding rate of 12 gmin−1, scanning speed of 12 mm s−1, shielding gas flow rate of 25 Lmin−1 and carrier gas flow rate of 4 Lmin−1 for a laser spot diameter of 2.1mm. Out of the cross-sectioned beads, their respective height, width and penetration were calculated with 2.71%, 4.01% and 9.35% errors; the dilution proportion was computed with 14.15% error, the area above the substrate with 5.27% error and the area below the substrate with 17.93% error. The average computational time for the processing of one image was 12.7s. The developed approach was purely segmentational and could potentially benefit from machine-learning implementations.

Electromagnetic Interference Simulation of Software Electronic Equipment Based on Efficient Time Domain Algorithm

In order to ensure the normal operation of software electronic equipment and better guide the electromagnetic protection design of software electronic equipment, a set of computational models and numerical methods are needed to analyze the electromagnetic interference problems of electronic equipment. To this end, a new field-path hybrid time domain algorithm is adopted to simulate the electromagnetic interference of broadband electromagnetic signals to software electronic equipment in the time domain; the results are compared with those of the FDTD method to verify the correctness and efficiency of the algorithm. The average calculation time of FDTD is 478.3 min, while that of the field-path hybrid time domain algorithm is 46.5 min. The results show that the simulation effect of the field-path hybrid time domain algorithm is consistent with that of FDTD and saves a lot of memory and computation time, which proves the correctness and efficiency of the algorithm.

The combination of gray level co-occurrence matrix and back propagation neural network for classifying stairs descent and floor

Smart wheelchairs (SW) technology is one of the solutions to help disabled people who do not have a hand or people to help them. Apart from able to move on its own, a smart wheelchair needs to be safe to use. One of the ways to increase SW safety is the ability to detect obstacles. In this study, we tried to create obstacle detection that can classify the stairs descent and floor based on image processing. To achieve our purpose, Contrast Limited Adaptive Histogram Equalization (CLAHE) is used to increase image contrast. After that, Gray Level Co-occurrence Matrix (GLCM) is used to extract features from the image. Finally, Back Propagation Neural Network (BPNN) is used to classify the image. Based on the test result, BPNN achieves results with 95% Accuracy, 95% Sensitivity, 95% Specificity with an average computation time of 0.0035 s.

Bivariate Polynomial Codes for Secure Distributed Matrix Multiplication

We consider the problem of secure distributed matrix multiplication (SDMM). Coded computation has been shown to be an effective solution in distributed matrix multiplication, both providing privacy against workers and boosting the computation speed by efficiently mitigating stragglers. In this work, we present a non-direct secure extension of the recently introduced bivariate polynomial codes. Bivariate polynomial codes have been shown to be able to further speed up distributed matrix multiplication by exploiting the partial work done by the stragglers rather than completely ignoring them while reducing the upload communication cost and/or the workers’ storage’s capacity needs. We show that, especially for upload communication or storage constrained settings, the proposed approach reduces the average computation time of SDMM compared to its competitors in the literature.

Local directional coding-based scene change detection for frame rate up-conversion

This paper proposes a new scene change detection method that uses local directional coding for frame rate up-conversion. The directional coding technique converts the luminance value of the edge direction response for given frames to bit codes and calculates the bit code difference between the previous and current frames. Existing scene change detection methods usually calculate the difference between the histogram shapes or the luminance values between the previous and current frames to detect scene changes. Thus, they erroneously detect scene changes in a scene with moving objects or camera motion. The existing automatic thresholding-based method uses iterative operations to calculate the optimal threshold and determine the scene change using the difference between the calculated threshold values, and it therefore has a high computational cost. To solve these problems, the proposed method uses the difference between the bit codes from the eight edge response values between the previous and current frames to detect the initial scene change regions. In addition, the proposed method uses a refinement process on the detected initial scene change regions to enhance the scene change detection accuracy. The experimental results showed that the proposed method enhanced average F1 score to 0.5235 (a 126.36 % improvement) as compared with the benchmark methods. The average computation time per pixel of the proposed method also reduced to 13.3668 μs (an 87.39 % reduction) compared with the benchmark methods.

Research on Data Mining Algorithm Based on BP Neural Network

The current data mining algorithm has the problem of imperfect data mining function, which leads to the algorithm taking too long time. This paper designs a data mining algorithm based on BP neural network. Analyze the basic structure of the data mining algorithm, obtain the data characteristics of the multi-objective decision-making, adjust the convergence speed with the distributed computing technology to keep the inertia factor state unchanged, construct the local minimal discrete model, measure the interest of the model, calculate the optimal output value of the network using the BP (Back Propagation) neural network model, and complete the improved design of the data mining function. Experimental results: The average computational time consumption of the designed data mining algorithm is 559.827 seconds, which saves 145.975 seconds and 174.237 seconds respectively than other traditional algorithms. It is proved that the data mining algorithm based on BP neural network reduces the computational time consumption, improves the performance of data mining, and has high application value.

Research on Data Mining Algorithm Based on BP Neural Network

The current data mining algorithm has the problem of imperfect data mining function, which leads to the algorithm taking too long time. This paper designs a data mining algorithm based on BP neural network. Analyze the basic structure of the data mining algorithm, obtain the data characteristics of the multi-objective decision-making, adjust the convergence speed with the distributed computing technology to keep the inertia factor state unchanged, construct the local minimal discrete model, measure the interest of the model, calculate the optimal output value of the network using the BP (Back Propagation) neural network model, and complete the improved design of the data mining function. Experimental results: The average computational time consumption of the designed data mining algorithm is 559.827 seconds, which saves 145.975 seconds and 174.237 seconds respectively than other traditional algorithms. It is proved that the data mining algorithm based on BP neural network reduces the computational time consumption, improves the performance of data mining, and has high application value.

A General Branch-and-Cut Framework for Rotating Workforce Scheduling

In this paper, we propose a general algorithmic framework for rotating workforce scheduling. We develop a graph representation that allows to model a schedule as a Eulerian cycle of stints, which we then use to derive a problem formulation that is compact toward the number of employees. We develop a general branch-and-cut framework that solves rotating workforce scheduling in its basic variant, as well as several additional problem variants that are relevant in practice. These variants comprise, among others, objectives for the maximization of free weekends and the minimization of employees. Our computational studies show that the developed framework constitutes a new state of the art for rotating workforce scheduling. For the first time, we solve all 6,000 instances of the status quo benchmark for rotating workforce scheduling to optimality with an average computational time of 0.07 seconds and a maximum computational time of 2.53 seconds. These results reduce average computational times by more than 99% compared with existing methods. Our algorithmic framework shows consistent computational performance, which is robust across all studied problem variants. Summary of Contribution: This paper proposes a novel exact algorithmic framework for the well-known rotating workforce scheduling problem (RWSP). Although the RWSP has been extensively studied in different problem variants and for different exact and heuristic solution approaches, the presented algorithmic framework constitutes a new state-of-the-art for the RWSP that solves all known benchmark sets to optimality and improves on the current state-of-the-art by orders of magnitude with respect to computational times, especially for large-scale instances. The paper is both of methodological value for researchers and of high interest for practitioners. For researchers, the presented framework is amenable for various problem variants and provides a common ground for further studies and research. For practitioners and software developers, low computational times of a few seconds allows the framework to be to embedded into personnel scheduling software.

In-situ layer-wise certification for direct laser deposition processes based on thermal image series analysis

In direct laser deposition (DLD) processes, process uncertainty leads to defects in the final product, which can significantly compromise product quality, mechanical properties, and reliability of the additively manufactured (AM) parts. Therefore, quality control and certification are of critical importance in the broader adoption of DLD processes. In-situ thermal history contains critical information of process quality and defect occurrences. This paper proposes a new layer-wise anomaly detection method for in-situ DLD process certification by leveraging thermal image series analysis. Image registration is leveraged to characterize the dynamics in the layer-wise thermal history, and Gaussian process (GP) models are used to characterize the variation component which is left unexplained by the image registration operation. Multiple new layer-wise features are extracted from the registration modeling and the GP models. Both a thin wall specimen and a cylindrical shaped specimen are used in the case study to demonstrate the effectiveness of the proposed method. When comparing with the benchmark method, the proposed method shows comparable results for the thin wall specimen, and it significantly outperforms the benchmark method for the cylindrical shaped specimen. In addition, the average computational time of the proposed method is significantly shorter than the average layer-wise build time, enabling the proposed method to facilitate in-situ anomaly detection and process control.

Geometry-aware fruit grasping estimation for robotic harvesting in apple orchards

Field robotic harvesting is a promising technique in recent development of agricultural industry. It is vital for robots to recognise and localise fruits before the harvesting in natural orchards. However, the workspace of harvesting robots in orchards is complex: many fruits are occluded by branches and leaves. It is important to estimate a proper grasping pose for each fruit before performing the manipulation. In this study, a geometry-aware network, A3N, is proposed to perform end-to-end instance segmentation and grasping estimation using both color and geometry sensory data from a RGB-D camera. Besides, workspace geometry modelling is applied to assist the robotic manipulation. Moreover, we implement a global-to-local scanning strategy, which enables robots to accurately recognise and retrieve fruits in field environments with two consumer-level RGB-D cameras. We also evaluate the accuracy and robustness of proposed network comprehensively in experiments. The experimental results show that A3N achieves 0.873 on instance segmentation accuracy, with an average computation time of 35 ms. The average accuracy of grasping estimation is 0.61 cm and 4.8$^{\circ}$ in centre and orientation, respectively. Overall, the robotic system that utilizes the global-to-local scanning and A3N, achieves success rate of harvesting ranging from 70\% - 85\% in field harvesting experiments.

Parallel CPU–GPU computing technique for discrete element method

AbstractThe efficiency of the simulations with the discrete element method (DEM) is significantly improved using a novel computational strategy. The new method is developed with a focus on platforms equipped with multi‐core central processing units (CPU) and general‐purpose graphics processing units (GPU). The DEM calculations are performed in parallel on the CPU and on the GPU using pre‐calculated Verlet lists with a posteriori analysis of their consistency. The operations related to the search for possible contacts are performed on the CPU, whereas the processing of interactions, and integration of motion, are executed on the GPU. Performance analysis done for various types of tasks has shown that the new method allows to significantly decrease the average computational time and to utilize available computational resources more efficiently compared to the sequential CPU–GPU execution mode. Furthermore, due to more efficient calculations, the overall energy requirement for the proposed strategy does not exceed the demand for conventional sequential CPU–GPU computations.

2D Geometric Object Shapes Detection and Classification

In computer vision, object detection is a basic process for advanced procedure forms such as object detecting, analyzing, tracking, etc., for further processes, features extraction play a vital part to identify the objects accurately. Most of the existing frameworks may not be able to distinguish the objects appropriately when different objects have a place to a single frame. In this work, an automatic detection and recognition system of two-dimensional geometric shapes have been proposed. Firstly applied Genetic Algorithm (GA) to fill the shape after performing proper segmentation pre-processing method. The proposed framework is able of identifying numerous objects in the input image, determining the sort of the identified object, and labeled the recognized objects. Statistical method has been applied for each shape to extract the objects corners' points by calculating the largest boundary to form the features vector. Ultimately, the identified objects are classified as geometrical shapes such as square, rectangular, triangular, or circular. The proposed method achieved high accuracy around 98.3%, and an average computational time 0.521 sec. as an effective classification technique.

The application of nonlinear programming on ration formulation for dairy cattle

The objective of this study was to compare the application of iterative linear programming (iteLP), sequential quadratic programming (SQP), and mixed-integer nonlinear programming-based deterministic global optimization (MINLP_DGO) on ration formulation for dairy cattle based on Nutrient Requirements of Dairy Cattle (NRC, 2001). Least-cost diets were formulated for lactating cows, dry cows, and heifers. Nutrient requirements including energy, protein, and minerals, along with other limitations on dry matter intake, neutral detergent fiber, and fat were considered as constraints. Five hundred simulations were conducted, with each simulation randomly selecting 3 roughages and 5 concentrates from the feed table in NRC (2001) as the feed resource for each of 3 animal groups. Among the 500 simulations for lactating cows, 57, 45, and 21 simulations did not yield a feasible solution when using iteLP, SQP, and MINLP_DGO, respectively. All the simulations for dry cows and heifers were feasible when using SQP and MINLP_DGO, but 49 and 11 infeasible simulations occurred when using iteLP for dry cows and heifers, respectively. The average ration costs per animal per day of the feasible solutions obtained by iteLP, SQP, and MINLP_DGO were $4.78 (±0.71), $4.45 (±0.65), and $4.44 (±0.65) for lactating cows; $2.39 (±0.52), $1.48 (±0.26), and $1.48 (±0.26) for dry cows; and $0.98 (±0.72), $0.97 (±0.15), and $0.91 (±0.14) for heifers, respectively. The average computation time of iteLP, SQP, and MINLP_DGO were 0.59 (±1.87) s, 1.15 (±0.62) s, and 58.69 (±68.45) s for lactating cows; 0.041 (±0.070) s, 0.76 (±0.37) s, and 14.84 (±39.09) s for dry cows; and 1.60 (±2.90) s, 0.51 (±0.19) s, and 16.45 (±45.56) s for heifers, respectively. In conclusion, iteLP had limited capability of formulating least-cost diets when nonlinearity existed in the constraints. Both SQP and MINLP_DGO handled the nonlinear constraints well, with SQP being faster, whereas MINLP_DGO was able to return a feasible solution under some situations where SQP could not.

The effect of few historical data on the performance of sample average approximation method for operating room scheduling

AbstractWe model the scheduling problem of a single operating room for outpatient surgery, with uncertain case durations and an objective function comprising waiting time, idle time, and overtime costs. This stochastic scheduling problem has been studied in diverse forms. One of the most common approaches used is the sample average approximation (SAA). Our contribution is to study the use of SAA to solve this problem under few historical data using families of log t distributions with varying degrees of freedom. We analyze the results of the SAA method in terms of optimality convergence, the effect of the number of scenarios, and average computational time. Given the case sequence, computational results demonstrate that SAA with an adequate number of scenarios performs close to the exact method. For example, we find that the optimality gap, in units of proportional weighted time, is relatively small when 500 scenarios are used: 99% of the instances have an optimality gap of less than 2.6 7% (1.74%, 1.23%) when there are 3 (9, many) historical samples. Increasing the number of SAA scenarios improves performance, but is not critical when the case sequence is given. However, choosing the number of SAA scenarios becomes critical when the same method is used to choose among sequencing heuristics when there are few historical data. For example, when there are only three (nine, many) historical samples, 99% of the instances have less than 25.38% (13.15%, 6.87%) penalty in using SAA with 500 scenarios to choose the best sequencing heuristic.

Luminance Level of Histogram-Based Scene-Change Detection for Frame Rate Up-Conversion

Scene change detection is an essential process of frame rate up-conversion (FRUC). The performance of FRUC highly dependents on the accuracy of scene change detection. This paper proposes a new scene-change detection method that uses analysis of luminance level of the histograms for FRUC. The histogram luminance level refers to the statistical average luminance value obtained from the generated histograms for each region. Existing histogram-based scene change methods calculate the difference between optimal threshold values using an automatic thresholding technique or extract the difference between the histogram shape to detect the scene change. The automatic thresholding method uses iterative operations—the difference between the histogram shape is simply a method of calculating the luminance difference for the current and previous frames. Thus, it requires many computational resources and incorrectly detects a scene change because calculating the histogram shape cannot reflect regional image characteristics. The proposed method addresses these problems using histogram luminance levels for each region in the given frames. It calculates the level differences between the previous and current frames to detect the initial scene change regions. Moreover, the proposed method refines the initial scene change regions by analyzing the distribution of surrounding detected regions and uses refinement to enhance scene-change detection accuracy. In the experimental results, the proposed method increased the average F1 score to 0.4816 (a 122.51% improvement) compared with the benchmark methods. The average computation time per pixel of the proposed method also decreased to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$13.5323 \,\,\mu \text{s}$ </tex-math></inline-formula> (a 87.06% reduction) compared with the benchmark methods.

Target Detection Algorithm in Crime Recognition Using Artificial Intelligence

Presently, suspect prediction of crime scenes can be considered as a classification task, which predicts the suspects based on the time, space, and type of crime. Performing digital forensic investigation in a big data environment poses several challenges to the investigational officer. Besides, the facial sketches are widely employed by the law enforcement agencies for assisting the suspect identification of suspects involved in crime scenes. The sketches utilized in the forensic investigations are either drawn by forensic artists or generated through the computer program (composite sketches) based on the verbal explanation given by the eyewitness or victim. Since this suspect identification process is slow and difficult, it is required to design a technique for a quick and automated facial sketch generation. Machine Learning (ML) and deep learning (DL) models find it useful to automatically support the decision of forensics experts. The challenge is the incorporation of the domain expert knowledge with DL models for developing efficient techniques to make better decisions. In this view, this study develops a new artificial intelligence (AI) based DL model with face sketch synthesis (FSS) for suspect identification (DLFSS-SI) in a big data environment. The proposed method performs preprocessing at the primary stage to improvise the image quality. In addition, the proposed model uses a DL based MobileNet (MN) model for feature extractor, and the hyper parameters of the MobileNet are tuned by quasi oppositional firefly optimization (QOFFO) algorithm. The proposed model automatically draws the sketches of the input facial images. Moreover, a qualitative similarity assessment takes place with the sketch drawn by a professional artist by the eyewitness. If there is a higher resemblance between the two sketches, the suspect will be determined. To validate the effective performance of the DLFSS-SI method, a detailed qualitative and quantitative examination takes place. The experimental outcome stated that the DLFSS-SI model has outperformed the compared methods in terms of mean square error (MSE), peak signal to noise ratio (PSNR), average actuary, and average computation time.

A Hierarchical Motion Planning Framework for Autonomous Driving in Structured Highway Environments

This paper presents an efficient hierarchical motion planning framework with a long planning horizon for autonomous driving in structured environments. A 3D motion planning with time information is a non-convex problem because there exists more than one local minimum point and various constraints such as roads and obstacles. Accordingly, to deal with high computational complexity and the problem of falling into a local minimum in an enormous solution space, a decoupled method is utilized, that consists of two steps: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Long-term</i> planning and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">short-term</i> planning. First, the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">long-term</i> planner provides reasonable far-sighted behavior through two processes. In the first process, a rough path that includes a driving strategy is generated in the 2D spatial space. Then, the jump point search algorithm is utilized with time information on the path to reduce the computational burden of A*, giving an acceptable quality of solution at the same time. In this step, a safe, comfortable, and dynamically feasible trajectory is generated. Next, the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">short-term</i> planner optimizes a short-sighted trajectory using particle swarm optimization. In this method, a steering angle set is encoded as a particle, resulting in a safe, comfortable, and kinodynamically feasible trajectory. The proposed algorithm is implemented and evaluated in a range of vehicle-in-the-loop simulation scenarios, which include various virtual static and dynamic obstacles generated by Intelligent Driver Model. In the evaluation results, the proposed method reduced the computation time by up to 0.696 s with increasing the step cost by up to about 3%. The proposed algorithm is executed every 100 ms for a planning horizon of 10 seconds, and the average computation time is 31 ms with the worst-case computation time of 94 ms.

An Effective Machine Learning Approach for Classifying Artefact-Free and Distorted Capnogram Segments Using Simple Time-Domain Features

Capnogram signal analysis has received considerable attention owing to its important applications in assessing cardiopulmonary functions. However, the automatic elimination of deformed parts of a capnogram waveform remains an open research problem. Herein, we introduce an automatic classification approach for discriminating artefact-free (regular) and distorted (irregular) segments of capnogram signals. The proposed features include Hjorth parameters and mean absolute deviation (MAD). The main advantage of these features is their simplicity, such that they can be employed in a computationally efficient machine learning algorithm. MATLAB simulation is conducted on 100 regular and 100 irregular segments of capnogram to extract the proposed and existing features, which are ranked based on the Pearson correlation coefficient, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${p}$ </tex-math></inline-formula> -value and area under receiver operating characteristic (ROC) curve. The naive Bayes, decision tree, random forest and support vector machine (SVM) classifiers are fed by the relatively highly ranked features, and the classification performance is assessed via ten-fold cross-validation. Besides the linear kernel SVM, the radial basis function (RBF) and polynomial kernel functions with different orders are also included in the current experiment. Results revealed the effectiveness of the Hjorth activity and MAD attributes when used with the fourth-order polynomial kernel-SVM classifier. The achieved accuracy, precision and specificity are 89%, 92.1%, and 91% outperforming the existing method by 2.5%, 5.6% and 7%, respectively. The simplicity of the proposed time-domain features is confirmed by the average total computational time of features extraction and classification phases which is only 13 ms instead of 19 ms in the case of incorporating both time- and frequency-domain features, indicating a reduction of 31.6%. It is envisaged that the proposed approach can be valuable if implemented with capnography devices for real-time and fully automated capnogram-based respiratory assessment. Even so, further research is recommended to enhance the classification performance through exploring more features and/or classifiers.

Towards sustainable smart cities: A secure and scalable trading system for residential homes using blockchain and artificial intelligence

• The paper proposes a secure blockchain based energy trading system for homes. • A new proof-of-computational closeness consensus protocol is proposed for selection of miners. • An analytical energy pricing policy is designed to solve the problem of existing energy pricing policies. • A dynamic multi-pseudonym is developed for prosumers for privacy during trading. • A Jaya optimization accelerates error convergence rate reducing connections between neurons layers This paper proposes a secure blockchain based energy trading system for residential homes. In the system, a new proof-of-computational closeness (PoCC) consensus protocol is proposed for the selection of miners and the creation of blocks. Moreover, an analytical energy pricing policy is designed to solve the problem of existing energy pricing policies in a distributed trading environment. A dynamic multi-pseudonym mechanism is developed for the prosumers to preserve their transactional privacy during energy trading. Since it requires extra storage and computing resources for the blockchain miners to simultaneously execute both mining process and application intensive tasks, therefore, an improved sparse neural network (ISNN) is proposed for computation offloading to the cloud servers. In ISNN, a Jaya optimization algorithm is used to accelerate the error convergence rate while reducing the number of connections between different layers of neurons. Besides, ISNN optimizes the overall computational cost of the system. Furthermore, the security of the prosumers is ensured using blockchain technology while security analysis shows that the system is robust against the Sybil attack. The proposed blockchain based peer-to-peer secure energy trading system is extremely important for sustainable cities and society. Simulations are conducted to evaluate the effectiveness of the proposed system. The proposed pricing policy is compared with time-of-use pricing, critical peak pricing and real-time pricing policies. From the results, it is proved that the prosumers achieve a higher degree of satisfaction and utility when using the proposed pricing policy. Moreover, the probability of a successful Sybil attack is zero as the number of attackers’ identities and computational capacities increases. Under different sizes of data to be uploaded, the proposed ISNN scheme has the least average computational cost and data transmission time as compared to deep reinforcement learning combined with genetic algorithm (DRGO) and sparse evolutionary training and multi-layer perceptron (SET-MLP) schemes in the literature. Moreover, the proposed system is tested for scalability by increasing the number of prosumers. Extensive simulations are performed and the results depict the satisfactory performance of the proposed system.