Pub Date : 2020-06-04DOI: 10.1088/2633-1357/ab8bc2
A. Parveen, Depanshu Varshney, J. Prakash
Here, we demonstrate experimentally the existence of temporally variable dielectric behavior of a nematic liquid crystal (NLC), the most widely used liquid crystal (LC) phase among all LCs materials, by mixing dimethylsulphoxide (DMSO) into former. The intermolecular interactions and nanosegregation of the molecular LC structures have influenced their self-assembly by mixing DMSO into it. We mainly examined the dielectric parameters such as dielectric permittivity, dielectric loss factor, and absorption/energy dissipation and observed that the NLC/DMSO mixture shows a nearly dielectric-conductor (D-C) transition as time passes. The presence of DMSO in this analysis was confirmed by Fourier transform infrared spectroscopy while time-dependent dielectric studies were carried out using dielectric spectroscopic techniques. The promising idea of showing D-C transition is truly proven that may open the possibilities for real-time variable and supercapacitors.
{"title":"Nematic liquid crystal/dimethylsulphoxide mixture based tuning condenser","authors":"A. Parveen, Depanshu Varshney, J. Prakash","doi":"10.1088/2633-1357/ab8bc2","DOIUrl":"https://doi.org/10.1088/2633-1357/ab8bc2","url":null,"abstract":"Here, we demonstrate experimentally the existence of temporally variable dielectric behavior of a nematic liquid crystal (NLC), the most widely used liquid crystal (LC) phase among all LCs materials, by mixing dimethylsulphoxide (DMSO) into former. The intermolecular interactions and nanosegregation of the molecular LC structures have influenced their self-assembly by mixing DMSO into it. We mainly examined the dielectric parameters such as dielectric permittivity, dielectric loss factor, and absorption/energy dissipation and observed that the NLC/DMSO mixture shows a nearly dielectric-conductor (D-C) transition as time passes. The presence of DMSO in this analysis was confirmed by Fourier transform infrared spectroscopy while time-dependent dielectric studies were carried out using dielectric spectroscopic techniques. The promising idea of showing D-C transition is truly proven that may open the possibilities for real-time variable and supercapacitors.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1088/2633-1357/ab8bc2","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48202675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1088/2633-1357/ab805d
Frederick F. C. Ng, R. Jiang, J. Chow
Purpose: This study suggested a new method predicting the dose-volume parameter for radiation treatment planning evaluation using machine learning, and to evaluate the performance of different learning algorithms in the parameter prediction. Methods: Dose distribution index (DDI) for fifty prostate volumetric modulated arc therapy plans were calculated, and compared to results predicted by machine learning using algorithms, namely, linear regression, tree regression, support vector machine (SVM) and Gaussian process regression (GPR). Root mean square error (RMSE), prediction speed and training time were determined to evaluate the performance of each algorithm. Results: From the results, it is found that the square exponential GPR algorithm had the smallest RMSE, relatively high prediction speed and short training time of 0.0038, 4,100 observation/s and 0.18 s, respectively. All linear regression, SVM and GPR algorithms performed well according to their RMSE in the range of 0.0038–0.0193. However, RMSE of the medium and coarse tree regression algorithms were found larger than 0.03, showing that they are not suitable for predicting DDI in this study. Conclusion: Machine learning can be used to predict dose-volume parameter such as DDI in radiation treatment planning QA. Selection of a suitable machine learning algorithm is important to determine the parameter effectively.
{"title":"Predicting radiation treatment planning evaluation parameter using artificial intelligence and machine learning","authors":"Frederick F. C. Ng, R. Jiang, J. Chow","doi":"10.1088/2633-1357/ab805d","DOIUrl":"https://doi.org/10.1088/2633-1357/ab805d","url":null,"abstract":"Purpose: This study suggested a new method predicting the dose-volume parameter for radiation treatment planning evaluation using machine learning, and to evaluate the performance of different learning algorithms in the parameter prediction. Methods: Dose distribution index (DDI) for fifty prostate volumetric modulated arc therapy plans were calculated, and compared to results predicted by machine learning using algorithms, namely, linear regression, tree regression, support vector machine (SVM) and Gaussian process regression (GPR). Root mean square error (RMSE), prediction speed and training time were determined to evaluate the performance of each algorithm. Results: From the results, it is found that the square exponential GPR algorithm had the smallest RMSE, relatively high prediction speed and short training time of 0.0038, 4,100 observation/s and 0.18 s, respectively. All linear regression, SVM and GPR algorithms performed well according to their RMSE in the range of 0.0038–0.0193. However, RMSE of the medium and coarse tree regression algorithms were found larger than 0.03, showing that they are not suitable for predicting DDI in this study. Conclusion: Machine learning can be used to predict dose-volume parameter such as DDI in radiation treatment planning QA. Selection of a suitable machine learning algorithm is important to determine the parameter effectively.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47155275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-05-29DOI: 10.1088/2633-1357/ab828c
J. Obiko, F. Mwema
This paper reports on the effect of sample geometry size on the metal flow behaviour using DeformTM 3D finite element simulation software. The simulation process was done at forging temperature of 1100 °C and upper die speed of 50 mm/second. The friction coefficient between the die and the sample interface was taken to be constant during the simulation process. The results of the effective stress and strain distribution in the deformed sample were reported. The results show that the effective stress and strain distribution in the deformed sample was non-uniformly distributed. The maximum effective strain occurred at the centre of the deformed sample for all the samples tested. The maximum effective stress occurred at the die-sample contact surface. At the contact surfaces, the effective stress decreased with a decrease in the sample size. The effective stress at the centre of the deformed sample increased with a decrease in the sample geometry size.
{"title":"Numerical simulation on the effect of sample geometry size on the metal flow behaviour during the forging process","authors":"J. Obiko, F. Mwema","doi":"10.1088/2633-1357/ab828c","DOIUrl":"https://doi.org/10.1088/2633-1357/ab828c","url":null,"abstract":"This paper reports on the effect of sample geometry size on the metal flow behaviour using DeformTM 3D finite element simulation software. The simulation process was done at forging temperature of 1100 °C and upper die speed of 50 mm/second. The friction coefficient between the die and the sample interface was taken to be constant during the simulation process. The results of the effective stress and strain distribution in the deformed sample were reported. The results show that the effective stress and strain distribution in the deformed sample was non-uniformly distributed. The maximum effective strain occurred at the centre of the deformed sample for all the samples tested. The maximum effective stress occurred at the die-sample contact surface. At the contact surfaces, the effective stress decreased with a decrease in the sample size. The effective stress at the centre of the deformed sample increased with a decrease in the sample geometry size.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1088/2633-1357/ab828c","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41858211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-05-29DOI: 10.1088/2633-1357/ab9221
Lauren Carter
IOP SciNotes is a peer-reviewed, open access journal from IOP Publishing that enables researchers across the physical and environmental sciences to publish shorter research results (and other related outputs) which may not be suited to the traditional full-length journal article format. Adopting open science practices IOP SciNotes has been designed to provide authors with publication credit for individual stages or units of their research work, allowing anyone to validate, share and discover a wider range of scientific material associated with the research process.
{"title":"Welcome to IOP SciNotes—a new open access journal for short research outputs across the physical and environmental sciences","authors":"Lauren Carter","doi":"10.1088/2633-1357/ab9221","DOIUrl":"https://doi.org/10.1088/2633-1357/ab9221","url":null,"abstract":"IOP SciNotes is a peer-reviewed, open access journal from IOP Publishing that enables researchers across the physical and environmental sciences to publish shorter research results (and other related outputs) which may not be suited to the traditional full-length journal article format. Adopting open science practices IOP SciNotes has been designed to provide authors with publication credit for individual stages or units of their research work, allowing anyone to validate, share and discover a wider range of scientific material associated with the research process.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44596659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-05-29DOI: 10.1088/2633-1357/ab7f83
Narinder Kumar, Pawan Singh, K. Thapa, Devesh Kumar
In present work, we report the N-(p-hexyloxy-benzylidene)–p-toluidine (HBT) liquid crystal (LC) molecule having maximum absorbance due to the O–C stretching (carbon atom of benzene ring) during the intermolecular interaction. Under the expansion of an external electric field, the HBT LC having nematic to smectic phase stability with adverse (negative values) order parameter and birefringence. The refractive index expresses stability in the nematic, smectic, and isotropic phases. The director angle maintains stability for the nematic phase in the adverse order and smectic phase stable in positive order.
{"title":"Molecular spectroscopy and adverse optical properties of N-(p-hexyloxy-benzylidene)–p-toluidine (HBT) liquid crystal molecule studied by DFT methodology","authors":"Narinder Kumar, Pawan Singh, K. Thapa, Devesh Kumar","doi":"10.1088/2633-1357/ab7f83","DOIUrl":"https://doi.org/10.1088/2633-1357/ab7f83","url":null,"abstract":"In present work, we report the N-(p-hexyloxy-benzylidene)–p-toluidine (HBT) liquid crystal (LC) molecule having maximum absorbance due to the O–C stretching (carbon atom of benzene ring) during the intermolecular interaction. Under the expansion of an external electric field, the HBT LC having nematic to smectic phase stability with adverse (negative values) order parameter and birefringence. The refractive index expresses stability in the nematic, smectic, and isotropic phases. The director angle maintains stability for the nematic phase in the adverse order and smectic phase stable in positive order.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1088/2633-1357/ab7f83","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45092291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-05-29DOI: 10.1088/2633-1357/ab8be0
J. Pearse, J. Chow
Purpose: We developed an app for Internet of Things (IoT) device such as smartphone or tablet to calculate the monitor unit in superficial and orthovoltage skin therapy. The app can run both on the Windows and Android operation system. Methods: The IoT app was created based on the formula to calculate the monitor unit in skin therapy using kV photon beams. The calculation was based on databases of dose variables such as relative exposure factor and backscatter factor. The calculation also considered the stand-off and stand-in correction according to the inverse-square and inverse-cube law. Verification of the app was carried out by comparing the monitor unit results with those from hand calculations. Results: The frontend window of the app provided a user-friendly interface to the user for inputting prescription dose, beam and treatment setup variables. The user could save the calculation record electronically, generate a printout or send it to other radiation staff using the IoT. Verification of the app showing that deviation between the monitor units calculated by the app and by hand is insignificant. Conclusion: The verified IoT app can effectively calculate the monitor unit in superficial and orthovoltage skin therapy. The app takes advantages of all innate features of IoT such as real time communication, Internet access, data transfer and sharing.
{"title":"An Internet of Things app for monitor unit calculation in superficial and orthovoltage skin therapy","authors":"J. Pearse, J. Chow","doi":"10.1088/2633-1357/ab8be0","DOIUrl":"https://doi.org/10.1088/2633-1357/ab8be0","url":null,"abstract":"Purpose: We developed an app for Internet of Things (IoT) device such as smartphone or tablet to calculate the monitor unit in superficial and orthovoltage skin therapy. The app can run both on the Windows and Android operation system. Methods: The IoT app was created based on the formula to calculate the monitor unit in skin therapy using kV photon beams. The calculation was based on databases of dose variables such as relative exposure factor and backscatter factor. The calculation also considered the stand-off and stand-in correction according to the inverse-square and inverse-cube law. Verification of the app was carried out by comparing the monitor unit results with those from hand calculations. Results: The frontend window of the app provided a user-friendly interface to the user for inputting prescription dose, beam and treatment setup variables. The user could save the calculation record electronically, generate a printout or send it to other radiation staff using the IoT. Verification of the app showing that deviation between the monitor units calculated by the app and by hand is insignificant. Conclusion: The verified IoT app can effectively calculate the monitor unit in superficial and orthovoltage skin therapy. The app takes advantages of all innate features of IoT such as real time communication, Internet access, data transfer and sharing.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1088/2633-1357/ab8be0","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44324928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-05-26DOI: 10.1088/2633-1357/ab8d1a
U. Marathe, Meghashree Padhan, J. Bijwe
High performance polymers such as Poly(ether ether ketone) (PEEK), Poly(aryl ether ketone) (PAEK), Poly(ether ketone ketone) (PEKK), etc exhibit high melting points, 343 °C, 373 °C and 338 °C respectively and very high melt viscosity. They do not have appropriate solvents, which could open the ways to process their fabric reinforced composites; by impregnation technique followed by compression molding. Film stacking and powder sprinkling are the only possible techniques, which lead to weak crossover points due to non-wetting by the resin and finally resulting in inferior mechanical and interfacial properties and high amount of voids. In order to solve these problems, a novel technique called impregnation-co-film (ICF) is explored in this work. Polyetherimide (PEI) (10 wt% in dichloromethane solution) pre-impregnated graphite fabric prepregs were used before applying film technique followed by compression molding. The study compares properties such as density, void content, flexural strength, impact strength, Interlaminar shear strength (ILSS), thermal stability (in air) and interface by field emission scanning electron microscopy for the composite prepared with film stacking technique and that by impregnation-co-film stacking technique. It was confirmed that the new ICF technique proved to be significantly promising than the older technique almost in all aspects with 120% improvement in ILSS, 127% in flexural strength and 200% decrease in void content.
{"title":"Graphite fabric reinforced PAEK composites by novel impregnation-co-film technique","authors":"U. Marathe, Meghashree Padhan, J. Bijwe","doi":"10.1088/2633-1357/ab8d1a","DOIUrl":"https://doi.org/10.1088/2633-1357/ab8d1a","url":null,"abstract":"High performance polymers such as Poly(ether ether ketone) (PEEK), Poly(aryl ether ketone) (PAEK), Poly(ether ketone ketone) (PEKK), etc exhibit high melting points, 343 °C, 373 °C and 338 °C respectively and very high melt viscosity. They do not have appropriate solvents, which could open the ways to process their fabric reinforced composites; by impregnation technique followed by compression molding. Film stacking and powder sprinkling are the only possible techniques, which lead to weak crossover points due to non-wetting by the resin and finally resulting in inferior mechanical and interfacial properties and high amount of voids. In order to solve these problems, a novel technique called impregnation-co-film (ICF) is explored in this work. Polyetherimide (PEI) (10 wt% in dichloromethane solution) pre-impregnated graphite fabric prepregs were used before applying film technique followed by compression molding. The study compares properties such as density, void content, flexural strength, impact strength, Interlaminar shear strength (ILSS), thermal stability (in air) and interface by field emission scanning electron microscopy for the composite prepared with film stacking technique and that by impregnation-co-film stacking technique. It was confirmed that the new ICF technique proved to be significantly promising than the older technique almost in all aspects with 120% improvement in ILSS, 127% in flexural strength and 200% decrease in void content.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47792008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-17DOI: 10.1088/2633-1357/abc870
Subhadip Roy, A. Nandi, P. Das, C. Mitra
In this work, we study the development of a coplanar waveguide (CPW) resonator and its use in an electron spin resonance (ESR) spectrometer. The CPW resonator is designed to operate in S-band (2-4 GHz), with a short circuit configuration leading to miniaturization. It is so constructed such that it has a characteristic impedance of 50 ohms. The resonator supports quasi-TEM mode of propagation owing to its uniplanar nature, demanding detailed electromagnetic simulation. The design parameters and the electromagnetic field distribution are obtained from the simulation. The resonator is fabricated using optical lithography with a rapid prototyping technique. The characteristic response of the resonator is measured by coupling it to a Vector Network Analyzer (VNA). The ESR absorption spectrum of free radical 2,2-diphenyl-1-picrylhydrazyl (DPPH) is captured by using this resonator in reflection geometry. The microwave magnetic field distribution at the sample position is investigated. The ascertained value of Lande g-factor is consistent with that reported in the literature. Spin sensitivity of the order of 1015 spins/gauss is achieved upon using this resonator at room temperature. The quality factor of this resonator is found to be low and this makes it suitable for use in a Pulsed ESR spectrometer.
{"title":"S-band electron spin resonance spectroscopy using a short-circuited coplanar waveguide resonator","authors":"Subhadip Roy, A. Nandi, P. Das, C. Mitra","doi":"10.1088/2633-1357/abc870","DOIUrl":"https://doi.org/10.1088/2633-1357/abc870","url":null,"abstract":"In this work, we study the development of a coplanar waveguide (CPW) resonator and its use in an electron spin resonance (ESR) spectrometer. The CPW resonator is designed to operate in S-band (2-4 GHz), with a short circuit configuration leading to miniaturization. It is so constructed such that it has a characteristic impedance of 50 ohms. The resonator supports quasi-TEM mode of propagation owing to its uniplanar nature, demanding detailed electromagnetic simulation. The design parameters and the electromagnetic field distribution are obtained from the simulation. The resonator is fabricated using optical lithography with a rapid prototyping technique. The characteristic response of the resonator is measured by coupling it to a Vector Network Analyzer (VNA). The ESR absorption spectrum of free radical 2,2-diphenyl-1-picrylhydrazyl (DPPH) is captured by using this resonator in reflection geometry. The microwave magnetic field distribution at the sample position is investigated. The ascertained value of Lande g-factor is consistent with that reported in the literature. Spin sensitivity of the order of 1015 spins/gauss is achieved upon using this resonator at room temperature. The quality factor of this resonator is found to be low and this makes it suitable for use in a Pulsed ESR spectrometer.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41578206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-08DOI: 10.1088/2633-1357/abad0e
Weiwei Jiang
In this note, we contribute a multi-language handwritten digit recognition dataset named MNIST-MIX, which is the largest dataset of the same type in terms of both languages and data samples. With the same data format with MNIST, MNIST-MIX can be seamlessly applied in existing studies for handwritten digit recognition. By introducing digits from 10 different languages, MNIST-MIX becomes a more challenging dataset and its imbalanced classification requires a better design of models. We also present the results of applying a LeNet model which is pre-trained on MNIST as the baseline.
{"title":"MNIST-MIX: a multi-language handwritten digit recognition dataset","authors":"Weiwei Jiang","doi":"10.1088/2633-1357/abad0e","DOIUrl":"https://doi.org/10.1088/2633-1357/abad0e","url":null,"abstract":"In this note, we contribute a multi-language handwritten digit recognition dataset named MNIST-MIX, which is the largest dataset of the same type in terms of both languages and data samples. With the same data format with MNIST, MNIST-MIX can be seamlessly applied in existing studies for handwritten digit recognition. By introducing digits from 10 different languages, MNIST-MIX becomes a more challenging dataset and its imbalanced classification requires a better design of models. We also present the results of applying a LeNet model which is pre-trained on MNIST as the baseline.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48381044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-21DOI: 10.1088/2633-1357/abcd29
Ajay K. Gogineni, S. Swayamjyoti, Devadatta Sahoo, K. Sahu, R. Kishore
Vulnerability detection and safety of smart contracts are of paramount importance because of their immutable nature. Symbolic tools like OYENTE and MAIAN are typically used for vulnerability prediction in smart contracts. As these tools are computationally expensive, they are typically used to detect vulnerabilities until some predefined invocation depth. These tools require more search time as the invocation depth increases. Since the use of smart contracts increases rapidly, their analysis becomes difficult using these traditional tools. Recently, a machine learning technique called Long Short Term Memory (LSTM) has been used to predict the vulnerability of a smart contract. In the present article, we present how to classify smart contracts into Suicidal, Prodigal, Greedy, or Normal categories using Average Stochastic Gradient Descent Weight-Dropped LSTM (AWD-LSTM), a variant of LSTM. We reduced the class imbalance by considering only distinct opcode combinations for normal contracts and achieved a weighted average F1 score of 90.0%. Such techniques can be utilized in real-time to analyze a large number of smart contracts and to improve their security.
{"title":"Multi-Class classification of vulnerabilities in smart contracts using AWD-LSTM, with pre-trained encoder inspired from natural language processing","authors":"Ajay K. Gogineni, S. Swayamjyoti, Devadatta Sahoo, K. Sahu, R. Kishore","doi":"10.1088/2633-1357/abcd29","DOIUrl":"https://doi.org/10.1088/2633-1357/abcd29","url":null,"abstract":"Vulnerability detection and safety of smart contracts are of paramount importance because of their immutable nature. Symbolic tools like OYENTE and MAIAN are typically used for vulnerability prediction in smart contracts. As these tools are computationally expensive, they are typically used to detect vulnerabilities until some predefined invocation depth. These tools require more search time as the invocation depth increases. Since the use of smart contracts increases rapidly, their analysis becomes difficult using these traditional tools. Recently, a machine learning technique called Long Short Term Memory (LSTM) has been used to predict the vulnerability of a smart contract. In the present article, we present how to classify smart contracts into Suicidal, Prodigal, Greedy, or Normal categories using Average Stochastic Gradient Descent Weight-Dropped LSTM (AWD-LSTM), a variant of LSTM. We reduced the class imbalance by considering only distinct opcode combinations for normal contracts and achieved a weighted average F1 score of 90.0%. Such techniques can be utilized in real-time to analyze a large number of smart contracts and to improve their security.","PeriodicalId":93771,"journal":{"name":"IOP SciNotes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44773316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：