Determination of stable structure of a cluster using convolutional neural network and particle swarm optimization

Mitra, Arka; Jana, Gourhari; Pal, Ranita; Gaikwad, Pratiksha; Sural, Shamik; Chattaraj, Pratim Kumar

doi:10.1007/s00214-021-02726-z

Cited by 16 publications

(9 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mitra et al proposed an intrusion detection model of wireless sensor networks based on the support vector machine, which was based on the network structure of clusters. e network was divided into three layers and each layer adaptively detected intrusion [6]. In order to reduce false positives of Trojan horse detection algorithms in smartphones, a voting algorithm based on multiple machine learning algorithms in wireless sensor networks was proposed.…”

Section: Literature Reviewmentioning

confidence: 99%

Research on Smartphone Trojan Detection Based on the Wireless Sensor Network

2022

Security and Communication Networks

View full text Add to dashboard Cite

In order to reduce false positives of Trojan horse detection algorithms in smartphones, a voting algorithm based on multiple machine learning algorithms in wireless sensor networks was proposed. Through setting up the experiment, the preliminary preparations of the experiment, including sample set selection, feature set extraction method, and algorithm effect evaluation criteria, were described first. The K-nearest neighbors algorithm, random forests algorithm, support vector machine, and voting algorithm were compared. The experimental results showed that SVM and KNN algorithms took the shortest time, about 0.3 seconds. Judging by the test results, the voting algorithm still performed the best among the four algorithms as the voting algorithm was an extension of the three machine learning algorithms. In these randomly selected samples, malicious programs and nonmalicious programs were successfully distinguished by the voting algorithm. As the amount of test data increased, the test results would be closer to the actual situation. Namely, the voting algorithm would also have a small probability of false positives, which could meet the design requirements of the system. It was concluded that the method could effectively reduce false positives of the Trojan horse detection algorithm in smartphones.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Research on Smartphone Trojan Detection Based on the Wireless Sensor Network

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…A CNN model is used for learning and predicting the energy of C 5 , N 4 2– , N 6 4– , Au n ( n = 2–8), and Au n Ag m (2 ≤ n + m ≤ 8) clusters. − Initially, several random geometries are produced using ADMP , simulation within a particular range in the 3-D space, followed by their energy calculation. The CNN model is then set up from this initial set to be used later to generate a large number of systems required while locating the GM.…”

Section: Soft Computing With Problem Solvingmentioning

confidence: 99%

Global Optimization: A Soft Computing Perspective

Pal

Das

Chattaraj

2023

J. Phys. Chem. Lett.

Self Cite

View full text Add to dashboard Cite

Tackling the problem of global optimization is one of the most important domains that physicists and chemists are working on. The use of soft computing (SC) techniques has made this easier by reducing nonlinearity and instability and making it technologically rich. This Perspective aims at explaining the basic mathematical models of the most efficient and commonly used SC techniques in computational chemistry for finding the global minimum (GM) energy structures of chemical systems. In this Perspective, we discuss the global optimizations of several chemical systems that our group has worked on using CNN, PSO, FA, ABC, BO, and some hybrid techniques, two of which are interfaced to achieve better-quality results.

show abstract

“…DFT-PSO adjusts each particle's trajectory at every time stamp while following the convergence criteria. We have successfully implemented these techniques to find the GM configurations for small-sized nonmetallic clusters such as Boron (B 5 and B 6 ) (Yuan et al, 2014), Carbon (C 5 ) (Jana et al, 2019), and polynitrogen clusters (N 4 2and N 6 4-) (Mitra et al, 2021), and metallic clusters such as Al 4 2- (Mitra et al, 2020), Au n (n 2-8), and Au n Ag m (2 ≤ n+m ≤ 8) (Mitra et al, 2021).…”

Section: Global Optimization Using Machine Learning Techniquesmentioning

confidence: 99%

Atomic Clusters: Structure, Reactivity, Bonding, and Dynamics

2021

Self Cite

View full text Add to dashboard Cite

Atomic clusters lie somewhere in between isolated atoms and extended solids with distinctly different reactivity patterns. They are known to be useful as catalysts facilitating several reactions of industrial importance. Various machine learning based techniques have been adopted in generating their global minimum energy structures. Bond-stretch isomerism, aromatic stabilization, Rener-Teller effect, improved superhalogen/superalkali properties, and electride characteristics are some of the hallmarks of these clusters. Different all-metal and nonmetal clusters exhibit a variety of aromatic characteristics. Some of these clusters are dynamically stable as exemplified through their fluxional behavior. Several of these cluster cavitands are found to be agents for effective confinement. The confined media cause drastic changes in bonding, reactivity, and other properties, for example, bonding between two noble gas atoms, and remarkable acceleration in the rate of a chemical reaction under confinement. They have potential to be good hydrogen storage materials and also to activate small molecules for various purposes. Many atomic clusters show exceptional opto-electronic, magnetic, and nonlinear optical properties. In this Review article, we intend to highlight all these aspects.

show abstract

Determination of stable structure of a cluster using convolutional neural network and particle swarm optimization

Cited by 16 publications

References 90 publications

Research on Smartphone Trojan Detection Based on the Wireless Sensor Network

Research on Smartphone Trojan Detection Based on the Wireless Sensor Network

Global Optimization: A Soft Computing Perspective

Atomic Clusters: Structure, Reactivity, Bonding, and Dynamics

Contact Info

Product

Resources

About