Pub Date : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036442
Raniah Zaheer, Humera Shaziya
Training the deep learning models involves learning of the parameters to meet the objective function. Typically the objective is to minimize the loss incurred during the learning process. In a supervised mode of learning, a model is given the data samples and their respective outcomes. When a model generates an output, it compares it with the desired output and then takes the difference of generated and desired outputs and then attempts to bring the generated output close to the desired output. This is achieved through optimization algorithms. An optimization algorithm goes through several cycles until convergence to improve the accuracy of the model. There are several types of optimization methods developed to address the challenges associated with the learning process. Six of these have been taken up to be examined in this study to gain insights about their intricacies. The methods investigated are stochastic gradient descent, nesterov momentum, rmsprop, adam, adagrad, adadelta. Four datasets have been selected to perform the experiments which are mnist, fashionmnist, cifar10 and cifar100. The optimal training results obtained for mnist is 1.00 with RMSProp and adam at epoch 200, fashionmnist is 1.00 with rmsprop and adam at epoch 400, cifar10 is 1.00 with rmsprop at epoch 200, cifar100 is 1.00 with adam at epoch 100. The highest testing results are achieved with adam for mnist, fashionmnist, cifar10 and cifar100 are 0.9826, 0.9853, 0.9855, 0.9842 respectively. The analysis of results shows that adam optimization algorithm performs better than others at testing phase and rmsprop and adam at training phase.
{"title":"A Study of the Optimization Algorithms in Deep Learning","authors":"Raniah Zaheer, Humera Shaziya","doi":"10.1109/ICISC44355.2019.9036442","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036442","url":null,"abstract":"Training the deep learning models involves learning of the parameters to meet the objective function. Typically the objective is to minimize the loss incurred during the learning process. In a supervised mode of learning, a model is given the data samples and their respective outcomes. When a model generates an output, it compares it with the desired output and then takes the difference of generated and desired outputs and then attempts to bring the generated output close to the desired output. This is achieved through optimization algorithms. An optimization algorithm goes through several cycles until convergence to improve the accuracy of the model. There are several types of optimization methods developed to address the challenges associated with the learning process. Six of these have been taken up to be examined in this study to gain insights about their intricacies. The methods investigated are stochastic gradient descent, nesterov momentum, rmsprop, adam, adagrad, adadelta. Four datasets have been selected to perform the experiments which are mnist, fashionmnist, cifar10 and cifar100. The optimal training results obtained for mnist is 1.00 with RMSProp and adam at epoch 200, fashionmnist is 1.00 with rmsprop and adam at epoch 400, cifar10 is 1.00 with rmsprop at epoch 200, cifar100 is 1.00 with adam at epoch 100. The highest testing results are achieved with adam for mnist, fashionmnist, cifar10 and cifar100 are 0.9826, 0.9853, 0.9855, 0.9842 respectively. The analysis of results shows that adam optimization algorithm performs better than others at testing phase and rmsprop and adam at training phase.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131946866","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 : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036327
C. Viknesh, Praveen Kumar, R. Seetharaman
Melanoma has been recognized as the most fatal form of skin cancer to occur in humans and its incidence is increasing in many decades. The primary cause of melanoma is the over-exposure to UV rays emanating from sunlight, in those with low levels of melanin. Dermoscopy is a noninvasive procedure used for the examination of internal skin lesions. As the proposed method is based on eye-deduction, diagnosis of melanoma at early stage is quite difficult for dermatologist. This paper presents a methodological approach to extract features for benign and melanocytic skin lesions based on the ABCD rule using SVM Classifier. The image of the skin lesion is pre- processed to remove unwanted hair and noise. The lesion is segmented from the pre-processed image. Shape and colour features are extracted from the segmented lesion based on the ABCD rule. From the obtained features, it is then classified as benign and malignant using SVM Classifier. Results is demonstrated for the proposed approach has a better segmentation compared to the other techniques, obtaining values of 70% sensitivity, 75% specificity, 72.5% accuracy.
{"title":"Computer Aided Diagnostic System for the Classification of Skin Cancer Using Dermoscopic Images","authors":"C. Viknesh, Praveen Kumar, R. Seetharaman","doi":"10.1109/ICISC44355.2019.9036327","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036327","url":null,"abstract":"Melanoma has been recognized as the most fatal form of skin cancer to occur in humans and its incidence is increasing in many decades. The primary cause of melanoma is the over-exposure to UV rays emanating from sunlight, in those with low levels of melanin. Dermoscopy is a noninvasive procedure used for the examination of internal skin lesions. As the proposed method is based on eye-deduction, diagnosis of melanoma at early stage is quite difficult for dermatologist. This paper presents a methodological approach to extract features for benign and melanocytic skin lesions based on the ABCD rule using SVM Classifier. The image of the skin lesion is pre- processed to remove unwanted hair and noise. The lesion is segmented from the pre-processed image. Shape and colour features are extracted from the segmented lesion based on the ABCD rule. From the obtained features, it is then classified as benign and malignant using SVM Classifier. Results is demonstrated for the proposed approach has a better segmentation compared to the other techniques, obtaining values of 70% sensitivity, 75% specificity, 72.5% accuracy.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120863808","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 : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036385
N. Shree, Keertana Kamesh, Sanchita Vishwa, R. RaviKumar, Rajeshwari Hegde, Sharath Kumar
The mobile network technology is developing rapidly and the importance of network security has soared higher. Network security is a major issue because of the increasing attacks every passing day. After analyzing the network information security elements, this paper describes the potential threats, types of network security attacks and also throws some light on the preventive methodologies existent and provides plausible suggestions for the improvement of the same.
{"title":"Security Challenges in Mobile Communication Networks","authors":"N. Shree, Keertana Kamesh, Sanchita Vishwa, R. RaviKumar, Rajeshwari Hegde, Sharath Kumar","doi":"10.1109/ICISC44355.2019.9036385","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036385","url":null,"abstract":"The mobile network technology is developing rapidly and the importance of network security has soared higher. Network security is a major issue because of the increasing attacks every passing day. After analyzing the network information security elements, this paper describes the potential threats, types of network security attacks and also throws some light on the preventive methodologies existent and provides plausible suggestions for the improvement of the same.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134096196","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 : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036352
K. Lakshmi, P. Srinivas, C. Anupama
This paper deals with the application of one of the most efficacious evolutionary algorithms Differential Evolution (DE) to tune a PID controller for the IR heating system. In various industrial and commercial applications, temperature control with energy efficiency becomes a vital task. Even though ON-OFF control is the simplest control technique, it leads to more power consumption. System identification is used here to develop the model of the IR heater. The traditional PID and DE-based PID controllers are designed and their performances are compared through simulation results. Further, experimental results are obtained with the controllers implemented using Arduino to validate the simulation results. DE-based PID controller is found to be an energy efficient method for IR heater temperature control system with improved time domain specifications.
{"title":"Differential Evolution based PID Controller Design for IR Heating System","authors":"K. Lakshmi, P. Srinivas, C. Anupama","doi":"10.1109/ICISC44355.2019.9036352","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036352","url":null,"abstract":"This paper deals with the application of one of the most efficacious evolutionary algorithms Differential Evolution (DE) to tune a PID controller for the IR heating system. In various industrial and commercial applications, temperature control with energy efficiency becomes a vital task. Even though ON-OFF control is the simplest control technique, it leads to more power consumption. System identification is used here to develop the model of the IR heater. The traditional PID and DE-based PID controllers are designed and their performances are compared through simulation results. Further, experimental results are obtained with the controllers implemented using Arduino to validate the simulation results. DE-based PID controller is found to be an energy efficient method for IR heater temperature control system with improved time domain specifications.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134426782","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 : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036466
Gajanan Patle, Ajinkya S. Gujarkar, Ektaa Meshram
Generally, a finding of a surprising data i.e. anomalies from discrete data leads towards the better cognizance of atypical direct of examples and to perceive the base of anomalies. Anomalies can be portrayed as the examples that don't have standard lead. It is similarly called as anomaly detection. Anomaly detection systems are generally used for deception detection in control cards, bank coercion; sort out interference et cetera. It tends to be escaped as, peculiarities, deviation, extraordinary cases or special case. Such kind of examples can't be seen to the symptomatic significance of a special case, as extraordinary inquiry till it has been joined honestly. A bundle examination procedure is used to perceive little scale clusters formed by these anomalies. In this paper, we demonstrate distinctive methods existed for perceiving anomalies from datasets which just recognizes the individual anomalies. Issue with particular anomaly detection technique that distinguishes anomalies using the entire features regularly disregard to recognize such anomalies. A technique to perceive cluster of bizarre data join indicate atypical territory of a little subset of features. This strategy uses an invalid model to for ordinary topic and after that distinctive test to distinguish all clusters of bizarre examples.
{"title":"A Survey on Anomalous Topic Discovery in High Dimensional Data","authors":"Gajanan Patle, Ajinkya S. Gujarkar, Ektaa Meshram","doi":"10.1109/ICISC44355.2019.9036466","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036466","url":null,"abstract":"Generally, a finding of a surprising data i.e. anomalies from discrete data leads towards the better cognizance of atypical direct of examples and to perceive the base of anomalies. Anomalies can be portrayed as the examples that don't have standard lead. It is similarly called as anomaly detection. Anomaly detection systems are generally used for deception detection in control cards, bank coercion; sort out interference et cetera. It tends to be escaped as, peculiarities, deviation, extraordinary cases or special case. Such kind of examples can't be seen to the symptomatic significance of a special case, as extraordinary inquiry till it has been joined honestly. A bundle examination procedure is used to perceive little scale clusters formed by these anomalies. In this paper, we demonstrate distinctive methods existed for perceiving anomalies from datasets which just recognizes the individual anomalies. Issue with particular anomaly detection technique that distinguishes anomalies using the entire features regularly disregard to recognize such anomalies. A technique to perceive cluster of bizarre data join indicate atypical territory of a little subset of features. This strategy uses an invalid model to for ordinary topic and after that distinctive test to distinguish all clusters of bizarre examples.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134399215","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 : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036462
Chethan M, Chandrashekar Dasari, Gaurav v Uttarkar, Sachin D N
Glaucoma is a group of eye disease which result in damage to the optic nerve and vision loss. The most common type is open angle glaucoma and closed angle glaucoma and this can be diagnosed using different machine learning models such as artificial nervous system and support vector machine and precision can be checked with machine learning characterizations (MLC) and RNAF. It guides him throughout the time. Machine learning can be used to automate the equipment, thereby minimizing the human effort.
{"title":"Diagnosis of Glaucoma using Machine Learning - A Survey","authors":"Chethan M, Chandrashekar Dasari, Gaurav v Uttarkar, Sachin D N","doi":"10.1109/ICISC44355.2019.9036462","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036462","url":null,"abstract":"Glaucoma is a group of eye disease which result in damage to the optic nerve and vision loss. The most common type is open angle glaucoma and closed angle glaucoma and this can be diagnosed using different machine learning models such as artificial nervous system and support vector machine and precision can be checked with machine learning characterizations (MLC) and RNAF. It guides him throughout the time. Machine learning can be used to automate the equipment, thereby minimizing the human effort.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131972701","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 : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036333
B. Sai, T. Sasikala
In this competitive world, transport services have become highly saturated. To operate an existing company or open a new company in the field of transport is very important and need to know the demand forecast. In the field of transport, service providers facing complex challenges due to the competitors. This paper explores the applications of a forecasting model to predict the number of passengers going to travel in the future. It also compares the efficiency of different models like Auto Regressive and Integrated Moving Average (ARIMA), HOLT WINTERS, Naïve, Snaïve, Drift and list their performances.
{"title":"Forecasting Air Passenger Data using various models","authors":"B. Sai, T. Sasikala","doi":"10.1109/ICISC44355.2019.9036333","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036333","url":null,"abstract":"In this competitive world, transport services have become highly saturated. To operate an existing company or open a new company in the field of transport is very important and need to know the demand forecast. In the field of transport, service providers facing complex challenges due to the competitors. This paper explores the applications of a forecasting model to predict the number of passengers going to travel in the future. It also compares the efficiency of different models like Auto Regressive and Integrated Moving Average (ARIMA), HOLT WINTERS, Naïve, Snaïve, Drift and list their performances.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134526231","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 : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036419
Terry Jacob Mathew, E. Sherly
The problems of today's real world decision making are mostly associated with an element of uncertainty. The soft set theory is a flexible mathematical tool that handles uncertainty, impreciseness, and vagueness in solving decision making problems. The applications span across different domains such as engineering, medical diagnosis, economics etc. In this paper, we present a review on soft sets and its hybrids related to applications in computer science. Researchers can benefit from this review to explore possible avenues of research by application of efficient and innovative methods.
{"title":"A Review on Soft Set-Based Theories Relevant to Decision Making in Computer Science","authors":"Terry Jacob Mathew, E. Sherly","doi":"10.1109/ICISC44355.2019.9036419","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036419","url":null,"abstract":"The problems of today's real world decision making are mostly associated with an element of uncertainty. The soft set theory is a flexible mathematical tool that handles uncertainty, impreciseness, and vagueness in solving decision making problems. The applications span across different domains such as engineering, medical diagnosis, economics etc. In this paper, we present a review on soft sets and its hybrids related to applications in computer science. Researchers can benefit from this review to explore possible avenues of research by application of efficient and innovative methods.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125557756","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 : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036353
A. Srisaila, S. Kranthi, K. Pranathi
Not all bugs prompt program crashes, and not generally is there a formal particular to check the accuracy of a product test's result. A typical situation in programming testing is in this way that test information are created, and an analyzer physically includes test prophets. There is, in any case, an essential issue with the normal approach of focusing on one scope objective at any given moment: Scope objectives are not independent, not just as difficult, Also at times infeasible and the consequence from claiming test era will be Hence reliant on the request for scope objectives what's more entryway Numerous about them need aid practical. To beat this problem, we recommend an novel standard done which entirety test suites would advanced with those point from claiming coating at scope objectives during the same chance same time keeping the aggregate measure Concerning illustration little Likewise conceivable. This methodology need a few advantages, With respect to example, its viability will be not influenced Toward the number for infeasible focuses in the code.
{"title":"Test Suite Generation Using Software Engineering Tool","authors":"A. Srisaila, S. Kranthi, K. Pranathi","doi":"10.1109/ICISC44355.2019.9036353","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036353","url":null,"abstract":"Not all bugs prompt program crashes, and not generally is there a formal particular to check the accuracy of a product test's result. A typical situation in programming testing is in this way that test information are created, and an analyzer physically includes test prophets. There is, in any case, an essential issue with the normal approach of focusing on one scope objective at any given moment: Scope objectives are not independent, not just as difficult, Also at times infeasible and the consequence from claiming test era will be Hence reliant on the request for scope objectives what's more entryway Numerous about them need aid practical. To beat this problem, we recommend an novel standard done which entirety test suites would advanced with those point from claiming coating at scope objectives during the same chance same time keeping the aggregate measure Concerning illustration little Likewise conceivable. This methodology need a few advantages, With respect to example, its viability will be not influenced Toward the number for infeasible focuses in the code.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130290073","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 : 2019-01-01DOI: 10.1109/ICISC44355.2019.9036394
A. Vaish, Mahender Singh, Supreet Kaur, P. Kumar
Little scale strip settle Antenna are astonishing for their inclination like light weight, low profile, diminished and easy to make. Littler scale strip settle Antennas are proposed to have diverse geometrical shapes and estimations. The square shape is the key and most much of the time used receiving wire because it used for the essential and most demandable applications. Regardless, surface wave activating isn't joking issue in cut back scale strip receiving wire since surface wave diminishes the social event mechanical party efficiency and purpose of containments the exchange speed. To vanquish this disadvantage, a test reinforced square fix with opening help has been sorted out and continued using IE3D fragile thing.
{"title":"Design and Analysis of Square microstrip patch Antenna with and without cavity backing","authors":"A. Vaish, Mahender Singh, Supreet Kaur, P. Kumar","doi":"10.1109/ICISC44355.2019.9036394","DOIUrl":"https://doi.org/10.1109/ICISC44355.2019.9036394","url":null,"abstract":"Little scale strip settle Antenna are astonishing for their inclination like light weight, low profile, diminished and easy to make. Littler scale strip settle Antennas are proposed to have diverse geometrical shapes and estimations. The square shape is the key and most much of the time used receiving wire because it used for the essential and most demandable applications. Regardless, surface wave activating isn't joking issue in cut back scale strip receiving wire since surface wave diminishes the social event mechanical party efficiency and purpose of containments the exchange speed. To vanquish this disadvantage, a test reinforced square fix with opening help has been sorted out and continued using IE3D fragile thing.","PeriodicalId":419157,"journal":{"name":"2019 Third International Conference on Inventive Systems and Control (ICISC)","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115644025","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：