38 research outputs found
Metaheuristic and exact approaches for cost optimization in multi-echelon multimodal transportation network
No full textThis study develops a framework for a multimodal transportation system comprising two different modes of transportation—airways and roadways within a multi-echelon supply chain network in B2C e-commerce platforms. In this study, an optimization model based on mixed-integer quadratic programming was formulated, the objective of which is to minimize the overall transportation cost for B2C e-commerce supply chain networks. The metaheuristic technique incorporating two varied approaches—exact optimization and a genetic algorithm—was employed to provide the solution for this proposed optimization model of multimodal transportation system. This metaheuristic technique-based optimization model was tested on simulated datasets created to develop and analyze different case scenarios for the stated multimodal transportation problem. The comparative analysis of these two solution approaches is provided from the perspective of experimental performance as well as theoretical consideration. The findings of study can be applied to multi-echelon multimodal transportation networks in real practices targeting overall cost reduction and profit maximization of the logistic services for B2C e-commerce platforms
Mathematical driven model for closed-loop supply chain network design
No full textThe closed-loop supply chain (CLSC) has gained popularity as a practical way to improve sustainability and resource efficiency in various industries. Unlike a linear supply chain, a CLSC adopts reverse logistics to recover, recycle, and reuse items or their components. This study creates a mathematical model for a reliable and effective CLSC model that integrates forward and reverse logistics operations to reduce costs, boost profits, and reduce environmental impact. A metaheuristic approach (Genetic Algorithm) is used to solve the model. The experimental findings show that the suggested strategy contributes in enhancing CLSC performance
Traffic Pattern Plot: video identification in encrypted network traffic
No full textMost of the internet traffic is encrypted and it is a challenge to identify streaming videos in the internet traffic. In this paper, we present a methodology named Traffic Pattern Plot (TPP) to identify video streams in encrypted network traffic. The proposed methodology plots the video traffic flows and uses a Convolutional Neural Network (CNN) to detect the videos. The results show that the traffic pattern plot generated from 120 seconds of sniffing network traffic is enough to identify the video even in the encrypted network traffic with 94% accuracy
Mathematical Analysis of Single and Two Phase Flow of Blood in Narrow Arteries with Multiple Contrictions
No full textThe pulsatile flow of blood in narrow arteries with multiple-stenoses under body acceleration is analyzed mathematically, treating blood as (i) single-phase Herschel-Bulkley fluid model and (ii) two-phase Herschel-Bulkley fluid model. The expressions for various flow quantities obtained by Sankar and Ismail (2010) for single-phase Herschel-Bulkley fluid model and Sankar (2010c) for two-phase Herschel-Bulkley fluid model are used to compute the data for comparing these fluid models in a new flow geometry. It is noted that the plug core radius, wall shear stress and longitudinal impedance to flow are marginally lower for two-phase H-B fluid model than those of the single-phase H-B fluid model. It is found that the velocity decreases significantly with the increase yield stress of the fluid and the reverse behavior is noticed for longitudinal impedance to flow. It is also noticed that the velocity distribution and flow rate are higher for two-phase Herschel-Bulkley fluid model than those of the single-phase Herschel-Bulkley fluid model. It is also recorded that the estimates of the mean velocity increase with the increase of the body acceleration and this behavior is reversed when the stenosis depth increases
Numerical solution of Generalized Burger-Huxley & Huxley’s equation using Deep Galerkin neural network method
No full textIn this paper, a deep learning algorithm based on Deep Galerkin method (DGM) is presented for the approximate solution of the generalized Burgers-Huxley equation (gBHE), and generalized Hux-ley’s equation (gHE). In this method, a deep neural network (DNN) is used for approximating the solution without generating mesh grid, which satisfies the di˙erential operator, boundary and initial conditions. DNN is trained on randomly selected batches of time and space points, thus helping to avoid forming a mesh. Adam optimizer is used for optimizing the parameters of the DNN. Further, the convergence of the cost function and convergence of the neural network to the exact solution is demonstrated. This method shows very encouraging results which have been compared with re-cent methods such as: A fourth order improved numerical scheme(FDS4), Adomain-decomposition method (ADM), Modified cubic B-spline di˙erential quadrature method (MCB- DQM), Variational iteration method(VIM), and others
He-Laplace Method for Linear and Nonlinear Partial Differential Equations
No full textA new treatment for homotopy perturbation method is introduced. The new treatment is called He-Laplace method which is the coupling of the Laplace transform and the homotopy perturbation method using He’s polynomials. The nonlinear terms can be easily handled by the use of He’s polynomials. The method is implemented on linear and nonlinear partial differential equations. It is found that the proposed scheme provides the solution without any discretization or restrictive assumptions and avoids the round-off errors
Forecasting the Sugarcane Yields Based on Meteorological Data Through Ensemble Learning
No full textAccurate prediction of sugarcane yields is crucial, particularly for developing countries like India, due to its economic significance and impact on farmers’ livelihood. Unexpected fluctuations in production can affect farmers’ income and the stability of the market, emphasizing the necessity of accurate forecasting to avoid adverse economic consequences. This research aims to enhance the precision of sugarcane yield prediction in India by developing a stacking ensemble learning model. The developed model incorporates the least absolute shrink and selection operator (LASSO), artificial neural network (ANN), and random forest (RF) as base models alongside random forest regression (RFR) and Ridge regression (RR) as meta-models and utilizes principal component analysis (PCA) and SHAPLEY values to reduce dimensions and explore feature correlations within the dataset. The data used in the study is obtained from ICRISAT and NASA databases covering 40 years (1982 to 2021) of meteorological information and sugarcane yield data across 24 districts of Uttar Pradesh, India. The model’s generalizability is further improved through 5-fold cross-validation. For comparison, the vector autoregression moving average (VARMA) statistical method was also applied and it was observed that the outcome was not desirable. The findings indicate the competence of stacking ensemble model over individual models like LASSO, ANN, KNN, RF, and SVR
Installation of Smog-Free Towers using novel Real Coded Genetic Algorithm
No full textThe circle packing problem involves finding the best way to place non-overlapping circles within a given space, while the smog-free tower installation problem aims to minimize the exposure of residents to secondhand smog by identifying the optimal tower locations. This study proposes a Real Coded Genetic Algorithm (RCGA) that uses real-valued representations of circle positions to solve the smog-free tower installation problem. A new crossover operator is introduced, combining the information from two parent solutions to generate two new offspring solutions. The operator uses a random crossover point and two scaling factors to control the amount of information exchanged. The performance of the operator is evaluated on CEC- benchmark problem set and compared to other commonly used operators, with results indicating that it produces high-quality solutions and outperforms other operators in terms of solution quality and convergence speed. This research contributes to developing effective optimization algorithms that can have important implications for improving public health and reducing the negative effects of secondhand smog
AI-assisted Computer Network Operations Testbed for Nature-Inspired Cyber Security based Adaptive Defense Simulation and Analysis
No full textIn the current ever-changing cybersecurity scenario, active cyber defense strategies are imperative. In this work, we present a standard testbed to measure the efficacy and efficiency of customized networks while analyzing various parameters during the active attack. The presented testbed can be used for analyzing the network behavior in presence of various types of attacks and can help in fine-tuning the proposed algorithm under observation. The proposed testbed will allow users to design, implement, and evaluate the active cyber defense mechanisms with good library support of nature-inspired and AI-based techniques. Network loads, number of clusters, types of home networks, and number of nodes in each cluster and network can be customized. While using the presented testbed and incorporating active-defense strategies on existing network architectures, users can also design and propose new network architectures for effective and safe operation. In this paper, we propose a unified and standard testbed for cyber defense strategy simulation and bench-marking, which would allow the users to investigate current approaches and compare them with others, while ultimately aiding in the selection of the best approach for a given network security situation. We have compared the network performance in difference scenarios namely, normal, under attack and under attack in presence of NICS-based adaptive defense mechanism and achieved stable experimental results. {The experimental results clearly show that the proposed testbed is able to simulate the network conditions effectively with minimum efforts in network configuration. The simulation results of defense mechanisms verified on the proposed testbed got the improvement on almost 80 percent while increasing the turnaround time to 1-2 percent. The applicability of proposed testbed in modern technologies like Fog Computing and Edge Computing is also discussed in this paper
Fitness Varying Gravitational Constant in GSA
No full textGravitational Search Algorithm (GSA) is a recent metaheuristic algorithm inspired by Newton's law of gravity and law of motion. In this search process, position change is based on the calculation of step size which depends upon a constant namely, Gravitational Constant (G). G is an exponentially decreasing function throughout the search process. Further, inspite of having different masses, the value of G remains same for each agent, which may cause inappropriate step size of agents for the next move, and thus leads the swarm towards stagnation or sometimes skipping the true optima.
To overcome stagnation, we first propose a gravitational constant having different scaling characteristics for different phase of the search process. Secondly, a dynamic behavior is introduced in this proposed gravitational constant which varies according to the fitness of the agents. Due to this behavior, the gravitational constant will be different for every agent based on its fitness and thus will help in controlling the acceleration and step sizes of the agents which further improve exploration and exploitation of the solution search space. The proposed strategy is tested over 23 well-known classical benchmark functions and 11 shifted and biased benchmark functions. Various statistical analyses and a comparative study with original GSA, Chaos-based GSA (CGSA), Bio-geography Based Optimization (BBO) and DBBO has been carried out
