Pub Date : 2019-08-01DOI: 10.1109/ICAEM.2019.8853756
Ahsan Shehzed, A. Jalal, Kibum Kim
Automated video surveillance addresses people's real-time observation to describe their behaviors and interactions. This paper presents a novel multi-person tracking system for crowd counting and normal/ abnormal events detection at indoor/outdoor surveillance environments. The proposed system consists of four modules: people detection, head-torso template extraction, tracking and crowd cluster analysis. Firstly, the system extracts human silhouettes using inverse transform as well as median filter reducing the cost of computing and handling various complex monitoring situations. Secondly, people are detected by their head torso due to less varied and hardly occluded. Thirdly, each person is tracked through consecutive frames using the Kalman filter techniques with Jaccard similarity and normalized cross-correlation. Finally, the template marking is used for crowd counting having cues localization and clustered via Gaussian mapping for normal/abnormal events detection. The experimental results on two challenging datasets of video surveillance such as PETS2009 and UMN crowd analysis datasets demonstrate that the proposed system provides 88.7% and 95.5% in terms of counting accuracy and detection rate.
{"title":"Multi-Person Tracking in Smart Surveillance System for Crowd Counting and Normal/Abnormal Events Detection","authors":"Ahsan Shehzed, A. Jalal, Kibum Kim","doi":"10.1109/ICAEM.2019.8853756","DOIUrl":"https://doi.org/10.1109/ICAEM.2019.8853756","url":null,"abstract":"Automated video surveillance addresses people's real-time observation to describe their behaviors and interactions. This paper presents a novel multi-person tracking system for crowd counting and normal/ abnormal events detection at indoor/outdoor surveillance environments. The proposed system consists of four modules: people detection, head-torso template extraction, tracking and crowd cluster analysis. Firstly, the system extracts human silhouettes using inverse transform as well as median filter reducing the cost of computing and handling various complex monitoring situations. Secondly, people are detected by their head torso due to less varied and hardly occluded. Thirdly, each person is tracked through consecutive frames using the Kalman filter techniques with Jaccard similarity and normalized cross-correlation. Finally, the template marking is used for crowd counting having cues localization and clustered via Gaussian mapping for normal/abnormal events detection. The experimental results on two challenging datasets of video surveillance such as PETS2009 and UMN crowd analysis datasets demonstrate that the proposed system provides 88.7% and 95.5% in terms of counting accuracy and detection rate.","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131469783","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 : 2019-08-01DOI: 10.1109/ICAEM.2019.8853727
R. Yousaf, Syed Irtiza Ali Shah
Solar pond is a stratified region which stores solar energy in the form of thermal energy up to 95°C in its saline storage zone. This energy is used in various industrial applications ranging from electricity generation and desalination to refrigeration and hot water consumption. The ability of a pond to collect and store thermal energy in storage zone is dependent on effective stratification to suppress natural thermal convection. Diffusion and high temperature gradients result in encroachment of convective zones and development of additional internal convective zones. This results in degradation of stratification hence reducing the thermal efficiency of solar pond. In this scenario, maintenance of salinity gradient comes into play which involves monitoring of different parameters of the stratified region and injecting the fluid through diffusers controlled by feedback and control mechanism. Over the past few decades various methodologies have been developed for optimized maintenance of the stratified region. This research has thoroughly analyzed the gradient maintenance techniques, specifically focusing on injection mediums and their effects on the salinity gradient maintenance. The two configurations of injection medium i.e. injection of highly turbulent columnar jets into homogeneous convective zones and the injection of low exit Froude number fluid through a disk-shaped diffuser (most common) are elaborately analyzed and compared. Moreover, the effect of size & shape of the injector slots and followed by fluid velocity of injector on the flow pattern exiting the injection medium has been thoroughly analyzed. The analysis and comparison of different gradient maintenance and formation techniques show that flow discharge through a half disc shaped diffuser with rectangular slots at Froude No ranging from 12–18 is optimum for the stratified region. The analysis of an optimized injection mechanism has enabled formation and maintenance of a linearly distributed stratified region in the non-convective zone (NCZ) resulting in more heat collection in the lower convective zone (LCZ).
{"title":"Formation and maintenance of salinity gradient in a solar pond using brine injection technique for linear stratification","authors":"R. Yousaf, Syed Irtiza Ali Shah","doi":"10.1109/ICAEM.2019.8853727","DOIUrl":"https://doi.org/10.1109/ICAEM.2019.8853727","url":null,"abstract":"Solar pond is a stratified region which stores solar energy in the form of thermal energy up to 95°C in its saline storage zone. This energy is used in various industrial applications ranging from electricity generation and desalination to refrigeration and hot water consumption. The ability of a pond to collect and store thermal energy in storage zone is dependent on effective stratification to suppress natural thermal convection. Diffusion and high temperature gradients result in encroachment of convective zones and development of additional internal convective zones. This results in degradation of stratification hence reducing the thermal efficiency of solar pond. In this scenario, maintenance of salinity gradient comes into play which involves monitoring of different parameters of the stratified region and injecting the fluid through diffusers controlled by feedback and control mechanism. Over the past few decades various methodologies have been developed for optimized maintenance of the stratified region. This research has thoroughly analyzed the gradient maintenance techniques, specifically focusing on injection mediums and their effects on the salinity gradient maintenance. The two configurations of injection medium i.e. injection of highly turbulent columnar jets into homogeneous convective zones and the injection of low exit Froude number fluid through a disk-shaped diffuser (most common) are elaborately analyzed and compared. Moreover, the effect of size & shape of the injector slots and followed by fluid velocity of injector on the flow pattern exiting the injection medium has been thoroughly analyzed. The analysis and comparison of different gradient maintenance and formation techniques show that flow discharge through a half disc shaped diffuser with rectangular slots at Froude No ranging from 12–18 is optimum for the stratified region. The analysis of an optimized injection mechanism has enabled formation and maintenance of a linearly distributed stratified region in the non-convective zone (NCZ) resulting in more heat collection in the lower convective zone (LCZ).","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133079790","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 : 2019-08-01DOI: 10.1109/ICAEM.2019.8853721
A. Rafique, A. Jalal, Abrar Ahmed
To examine the features of complex visual world, sensor technology merged with objects characteristics to scenes well. These scenes understanding are highly demanding task in different domains of visionary technologies like autonomous driving, generic object detection, sports scene identification and security. In this paper, we proposed a novel statistical segmented framework that can learn robust scene model and separate each object component. Then, each component is used to extract geometrical features that concatenate extreme points features, orientation and polygon displacement values. These features help in object detection and Gaussian Naïve Bayes is used for the scene recognition. The experimental evaluation demonstrated the proposed approach over UIUC Sports and 15 Scene datasets that achieved scene recognition rate of 85.09% and 82.65%. The proposed system should be applicable to different emerging technologies such as augmented reality scene integration, GPS location finder and visual surveillance which recognized different locations/objects to understand real world scenes.
{"title":"Scene Understanding and Recognition: Statistical Segmented Model using Geometrical Features and Gaussian Naïve Bayes","authors":"A. Rafique, A. Jalal, Abrar Ahmed","doi":"10.1109/ICAEM.2019.8853721","DOIUrl":"https://doi.org/10.1109/ICAEM.2019.8853721","url":null,"abstract":"To examine the features of complex visual world, sensor technology merged with objects characteristics to scenes well. These scenes understanding are highly demanding task in different domains of visionary technologies like autonomous driving, generic object detection, sports scene identification and security. In this paper, we proposed a novel statistical segmented framework that can learn robust scene model and separate each object component. Then, each component is used to extract geometrical features that concatenate extreme points features, orientation and polygon displacement values. These features help in object detection and Gaussian Naïve Bayes is used for the scene recognition. The experimental evaluation demonstrated the proposed approach over UIUC Sports and 15 Scene datasets that achieved scene recognition rate of 85.09% and 82.65%. The proposed system should be applicable to different emerging technologies such as augmented reality scene integration, GPS location finder and visual surveillance which recognized different locations/objects to understand real world scenes.","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115760360","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 : 2019-08-01DOI: 10.1109/icaem.2019.8853772
{"title":"ICAEM Organizing Committee","authors":"","doi":"10.1109/icaem.2019.8853772","DOIUrl":"https://doi.org/10.1109/icaem.2019.8853772","url":null,"abstract":"","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114541785","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 : 2019-08-01DOI: 10.1109/ICAEM.2019.8853684
Muhammad Umar Khan, Sumair Aziz, M. Bilal, Muhammad Bilal Aamir
The electromyographic (EMG) signal generated in muscle fibers has been the topic under substantial research in immediate past years as it provides fairly large amount of information for assessment of neuromuscular diseases particularly amyotrophic lateral sclerosis (ALS). Besides this, the design of an accurate and computationally efficient diagnostic system remains a challenge due to variation of EMG signals taken from different muscles with different level of needle insertion. This study offers a complete framework for accurate classification of EMG signals which includes denoising by empirical mode decomposition (EMD), feature extraction from both the time and frequency domains and classification by logistic regression (LR) and support vector machine (SVM). The presented work efficiently discriminates between EMG signal of healthy subject and patient with ALS disease independent of which muscle is used for EMG signal acquisition and what insertion level of needle is. Performance evaluation measures such as sensitivity, specificity, F-measure, total classification accuracy and area under ROC curve (AVC) are used to validate the performance of both classifiers. LR classification technique shows superlative performance with a classification accuracy of 95.1%. These results shows the competence of proposed diagnostic system for classification of EMG signals. Moreover, the proposed method can be used in clinical applications for diagnoses of neuromuscular diseases.
{"title":"Classification of EMG Signals for Assessment of Neuromuscular Disorder using Empirical Mode Decomposition and Logistic Regression","authors":"Muhammad Umar Khan, Sumair Aziz, M. Bilal, Muhammad Bilal Aamir","doi":"10.1109/ICAEM.2019.8853684","DOIUrl":"https://doi.org/10.1109/ICAEM.2019.8853684","url":null,"abstract":"The electromyographic (EMG) signal generated in muscle fibers has been the topic under substantial research in immediate past years as it provides fairly large amount of information for assessment of neuromuscular diseases particularly amyotrophic lateral sclerosis (ALS). Besides this, the design of an accurate and computationally efficient diagnostic system remains a challenge due to variation of EMG signals taken from different muscles with different level of needle insertion. This study offers a complete framework for accurate classification of EMG signals which includes denoising by empirical mode decomposition (EMD), feature extraction from both the time and frequency domains and classification by logistic regression (LR) and support vector machine (SVM). The presented work efficiently discriminates between EMG signal of healthy subject and patient with ALS disease independent of which muscle is used for EMG signal acquisition and what insertion level of needle is. Performance evaluation measures such as sensitivity, specificity, F-measure, total classification accuracy and area under ROC curve (AVC) are used to validate the performance of both classifiers. LR classification technique shows superlative performance with a classification accuracy of 95.1%. These results shows the competence of proposed diagnostic system for classification of EMG signals. Moreover, the proposed method can be used in clinical applications for diagnoses of neuromuscular diseases.","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127122827","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 : 2019-08-01DOI: 10.1109/ICAEM.2019.8853728
Muhammad Nadeem, M. Z. Zeb, K. Imran, Abdul Kashif Janjua
Power system in stressed condition due to contingencies or overloading can lead to voltage collapse and can no longer operate in the secure region. Flexible AC transmission System (FACTS) devices plays key role in improving power system security and reliability. However, their optimal placement is necessary due to their high installation cost. In this paper Thyristor controlled series compensator (TCSC) are used for solving line overloads by controlling active power and static VAR compensator (SVC) are used for solving low voltages by controlling reactive power. Sensitivity based approach is used to find optimal placement of FACTs devices and PSO is utilized to find optimal size with objective to reduce real power loses and voltage deviations The indices are calculated for both normal condition and under severe contingencies. The Algorithm is applied on 30 bus test system and maximum loading factor are calculated with different combination of FACTS placed at their optimal positions. The study shows that there is improvement in voltage profile, voltage stability, loading parameter and reduction in active power losses.
{"title":"Optimal Sizing and Allocation of SVC and TCSC for reactive Power planning in Meshed Network","authors":"Muhammad Nadeem, M. Z. Zeb, K. Imran, Abdul Kashif Janjua","doi":"10.1109/ICAEM.2019.8853728","DOIUrl":"https://doi.org/10.1109/ICAEM.2019.8853728","url":null,"abstract":"Power system in stressed condition due to contingencies or overloading can lead to voltage collapse and can no longer operate in the secure region. Flexible AC transmission System (FACTS) devices plays key role in improving power system security and reliability. However, their optimal placement is necessary due to their high installation cost. In this paper Thyristor controlled series compensator (TCSC) are used for solving line overloads by controlling active power and static VAR compensator (SVC) are used for solving low voltages by controlling reactive power. Sensitivity based approach is used to find optimal placement of FACTs devices and PSO is utilized to find optimal size with objective to reduce real power loses and voltage deviations The indices are calculated for both normal condition and under severe contingencies. The Algorithm is applied on 30 bus test system and maximum loading factor are calculated with different combination of FACTS placed at their optimal positions. The study shows that there is improvement in voltage profile, voltage stability, loading parameter and reduction in active power losses.","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"101 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130513457","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}
With the emergence of IoT, wearable devices are drawing attention and becoming part of our daily life. These wearable devices collect private information about their wearers. Mostly, a secure authentication process is used to verify a legitimate user that relies on the mobile terminal. Similarly, remote cloud services are used for verification and authentication of both wearable devices and wearers. Security is necessary to preserve the privacy of users. Some traditional authentication protocols are proposed which have vulnerabilities and are prone to different attacks like forgery, de-synchronization, and un-traceability issues. To address these vulnerabilities, recently, Wu et al. (2017) proposed a cloud-assisted authentication scheme which is costly in terms of computations required. Therefore this paper proposed an improved, lightweight and computationally efficient authentication scheme for wearable devices. The proposed scheme provides similar level of security as compared to Wu's (2017) scheme but requires 41.2% lesser computations.
{"title":"Enhanced Lightweight Cloud-assisted Mutual Authentication Scheme for Wearable Devices","authors":"Mehmood Hassan, Khwaja Mansoor, Shahzaib Tahir, Waseem Iqbal","doi":"10.1109/ICAEM.2019.8853659","DOIUrl":"https://doi.org/10.1109/ICAEM.2019.8853659","url":null,"abstract":"With the emergence of IoT, wearable devices are drawing attention and becoming part of our daily life. These wearable devices collect private information about their wearers. Mostly, a secure authentication process is used to verify a legitimate user that relies on the mobile terminal. Similarly, remote cloud services are used for verification and authentication of both wearable devices and wearers. Security is necessary to preserve the privacy of users. Some traditional authentication protocols are proposed which have vulnerabilities and are prone to different attacks like forgery, de-synchronization, and un-traceability issues. To address these vulnerabilities, recently, Wu et al. (2017) proposed a cloud-assisted authentication scheme which is costly in terms of computations required. Therefore this paper proposed an improved, lightweight and computationally efficient authentication scheme for wearable devices. The proposed scheme provides similar level of security as compared to Wu's (2017) scheme but requires 41.2% lesser computations.","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131336375","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 : 2019-08-01DOI: 10.1109/ICAEM.2019.8853780
Muhammad Sharjeel Zareen, Shahzaib Tahir, M. Akhlaq, B. Aslam
Internet of Things (IoT) is progressing at a fast pace. Issues of security and privacy, emerged with introduction of IoT in late nineties, are still amongst the main challenges. In security issues, authentication and authorization of edge devices are main concerns due to resource constrained nature of edge devices. Various solutions have been proposed in the past to address said concerns but most of the solutions are based on increasing the computational capacity, storage and power in edge devices. However, said solutions are not practical since these solutions are either not possible due to small size of edge devices of IoT or not economical for their wide spread adoption. Some of the solutions also suggest the use of light weight cryptographic primitives. However, same are also not practical since all edge devices do not have requisite resources to implement these solutions. This paper proposes use of Artificial Intelligence (AI)/ machine learning in addressing the issues of authentication and authorization in edge devices. Proposed solution is based on fog computing model within a framework of a smart house but without reliance on computational capacity, storage or power of edge devices.
{"title":"Artificial Intelligence/ Machine Learning in IoT for Authentication and Authorization of Edge Devices","authors":"Muhammad Sharjeel Zareen, Shahzaib Tahir, M. Akhlaq, B. Aslam","doi":"10.1109/ICAEM.2019.8853780","DOIUrl":"https://doi.org/10.1109/ICAEM.2019.8853780","url":null,"abstract":"Internet of Things (IoT) is progressing at a fast pace. Issues of security and privacy, emerged with introduction of IoT in late nineties, are still amongst the main challenges. In security issues, authentication and authorization of edge devices are main concerns due to resource constrained nature of edge devices. Various solutions have been proposed in the past to address said concerns but most of the solutions are based on increasing the computational capacity, storage and power in edge devices. However, said solutions are not practical since these solutions are either not possible due to small size of edge devices of IoT or not economical for their wide spread adoption. Some of the solutions also suggest the use of light weight cryptographic primitives. However, same are also not practical since all edge devices do not have requisite resources to implement these solutions. This paper proposes use of Artificial Intelligence (AI)/ machine learning in addressing the issues of authentication and authorization in edge devices. Proposed solution is based on fog computing model within a framework of a smart house but without reliance on computational capacity, storage or power of edge devices.","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126464614","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 : 2019-08-01DOI: 10.1109/icaem.2019.8853653
{"title":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","authors":"","doi":"10.1109/icaem.2019.8853653","DOIUrl":"https://doi.org/10.1109/icaem.2019.8853653","url":null,"abstract":"","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114324199","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 : 2019-08-01DOI: 10.1109/ICAEM.2019.8853724
V. Gorbachenko, Mohie M. Alqezweeni
The learning of radial basis functions networks for solving approximation problems and partial differential equations is considered. Realizations of the accelerated gradient of Nesterov and Le-venberg-Marquardt were proposed for learning networks, which made it possible to significantly reduce the training time.
{"title":"Improving algorithms for learning of radial basis functions networks for approximation problems and solving partial differential equations","authors":"V. Gorbachenko, Mohie M. Alqezweeni","doi":"10.1109/ICAEM.2019.8853724","DOIUrl":"https://doi.org/10.1109/ICAEM.2019.8853724","url":null,"abstract":"The learning of radial basis functions networks for solving approximation problems and partial differential equations is considered. Realizations of the accelerated gradient of Nesterov and Le-venberg-Marquardt were proposed for learning networks, which made it possible to significantly reduce the training time.","PeriodicalId":304208,"journal":{"name":"2019 International Conference on Applied and Engineering Mathematics (ICAEM)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122113551","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：