Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987829
Saidatt Amonkar, Anikumar Naik, Amogh Sanzgiri
Automatic vehicle record-keeping systems have varied applications such as security for car parking facilities, tracking vehicle location and monitoring vehicular traffic. In this paper, we propose a system for vehicle authentication, book-keeping and tracking. The proposed system implements Automatic License Plate Recognition (ALPR) with Convolution Neural Network (CNN) followed by a Gated Recurrent Unit (GRU), which recognizes vehicles and automatically authenticates them with the records on a database to provide information about the vehicle. On the request of the vehicle owner, the system can send vehicle location data through SMS (Short Message Service) notification to the vehicle owner by using a GSM module. Tradition ALPR Systems employ Image Segmentation followed by individual character classification. In this work, we have used a sequence modeling technique that does not require image segmentation. It achieved a character recognition accuracy of 98% and a complete license plate character recognition accuracy of 88%, when trained on a modest data set consisting of 400 images of different fonts.
{"title":"ALPR System Using Sequence Modelling: A real time system for vehicle authentication","authors":"Saidatt Amonkar, Anikumar Naik, Amogh Sanzgiri","doi":"10.1109/ICSSIT46314.2019.8987829","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987829","url":null,"abstract":"Automatic vehicle record-keeping systems have varied applications such as security for car parking facilities, tracking vehicle location and monitoring vehicular traffic. In this paper, we propose a system for vehicle authentication, book-keeping and tracking. The proposed system implements Automatic License Plate Recognition (ALPR) with Convolution Neural Network (CNN) followed by a Gated Recurrent Unit (GRU), which recognizes vehicles and automatically authenticates them with the records on a database to provide information about the vehicle. On the request of the vehicle owner, the system can send vehicle location data through SMS (Short Message Service) notification to the vehicle owner by using a GSM module. Tradition ALPR Systems employ Image Segmentation followed by individual character classification. In this work, we have used a sequence modeling technique that does not require image segmentation. It achieved a character recognition accuracy of 98% and a complete license plate character recognition accuracy of 88%, when trained on a modest data set consisting of 400 images of different fonts.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121386950","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 : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987737
Rishhabh Naik, S. Vaishnavi, Jayashree M Oli, M. Vinodhini
With the increase in population, the time taken for the commute from one place to another is extremely important. As such, air travel has been the most preferred mode of transport due to its ability to cover large distances in short periods of time. As a result, it becomes very important to ensure the safety of passengers. As seen in a few instances in the past, lives have been put in jeopardy and extensive damage has been done both in terms of capital and people. We propose a proof of concept for an anti-hijacking system based on the ubiquitous RFID technology.
{"title":"Anti-Hijacking system using Raspberry Pi","authors":"Rishhabh Naik, S. Vaishnavi, Jayashree M Oli, M. Vinodhini","doi":"10.1109/ICSSIT46314.2019.8987737","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987737","url":null,"abstract":"With the increase in population, the time taken for the commute from one place to another is extremely important. As such, air travel has been the most preferred mode of transport due to its ability to cover large distances in short periods of time. As a result, it becomes very important to ensure the safety of passengers. As seen in a few instances in the past, lives have been put in jeopardy and extensive damage has been done both in terms of capital and people. We propose a proof of concept for an anti-hijacking system based on the ubiquitous RFID technology.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124037970","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 : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987875
E. Elamaran, B. Sudhakar
Any resource block with the period and the spacing, which enable feedback on the channel quality, which allow the scheduler in the downlink with the optimization of channel utility. A control of data traffic over the 5G network be the challenging task. In this paper the proposed work can overcome the challenges by using the design frame work based on the resource scheduling by using the Greedy based round Robin Scheduling (GBRRS) method, which control the data allocation from the initial level inside of the User Equipment (UE) of the resource scheduling blocks, the scheduling algorithm used in the radio segmentation processes. The long distance of the greedy scheduling and the rounding off specific task can be overcome by using the proposed algorithm. The performance evaluation based on the path loss, throughput, QoS violation probability and user capacities by using the simulation implemented in the mat lab R2014b.
{"title":"Greedy Based Round Robin scheduling solution for Data Traffic management in 5G","authors":"E. Elamaran, B. Sudhakar","doi":"10.1109/ICSSIT46314.2019.8987875","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987875","url":null,"abstract":"Any resource block with the period and the spacing, which enable feedback on the channel quality, which allow the scheduler in the downlink with the optimization of channel utility. A control of data traffic over the 5G network be the challenging task. In this paper the proposed work can overcome the challenges by using the design frame work based on the resource scheduling by using the Greedy based round Robin Scheduling (GBRRS) method, which control the data allocation from the initial level inside of the User Equipment (UE) of the resource scheduling blocks, the scheduling algorithm used in the radio segmentation processes. The long distance of the greedy scheduling and the rounding off specific task can be overcome by using the proposed algorithm. The performance evaluation based on the path loss, throughput, QoS violation probability and user capacities by using the simulation implemented in the mat lab R2014b.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126364011","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 : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987830
M. Vigil, M. Barhanpurkar, NS Rahul Anand, Yash Soni, Anmol Anand
YOLO (You Only Look Once) is a state of the art object detection system. The object detection algorithms of YOLO is taken and is used on a custom made dataset to identify the person on camera. This method will revolutionize surveillance and security methods. This paper addresses fundamental challenges faced in making the dataset. It also compares conventional methods with YOLO. YOLO is the fastest and most accurate object detection technique. This paper also states the applications of this technology along with its advantages and various disadvantages. It uses a multi-scale training method that can run at various sizes offering an excellent relation speed and accuracy. We have based our model on yolo v2 all the while bringing our own changes for shifting from object detection to Face identification.
YOLO (You Only Look Once)是一种最先进的物体检测系统。采用YOLO的目标检测算法，并在自定义数据集上对相机上的人进行识别。这种方法将彻底改变监视和安全方法。本文解决了在制作数据集时面临的基本挑战。它还比较了传统方法和YOLO。YOLO是最快和最准确的目标检测技术。本文还阐述了该技术的应用以及它的优点和各种缺点。它使用多尺度训练方法，可以在各种规模上运行，提供了良好的速度和准确性关系。我们的模型一直基于yolo v2，同时将我们自己的变化从物体检测转移到人脸识别。
{"title":"EYE SPY Face Detection and Identification using YOLO","authors":"M. Vigil, M. Barhanpurkar, NS Rahul Anand, Yash Soni, Anmol Anand","doi":"10.1109/ICSSIT46314.2019.8987830","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987830","url":null,"abstract":"YOLO (You Only Look Once) is a state of the art object detection system. The object detection algorithms of YOLO is taken and is used on a custom made dataset to identify the person on camera. This method will revolutionize surveillance and security methods. This paper addresses fundamental challenges faced in making the dataset. It also compares conventional methods with YOLO. YOLO is the fastest and most accurate object detection technique. This paper also states the applications of this technology along with its advantages and various disadvantages. It uses a multi-scale training method that can run at various sizes offering an excellent relation speed and accuracy. We have based our model on yolo v2 all the while bringing our own changes for shifting from object detection to Face identification.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125753847","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 : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987874
K. Veerasekaran, P. Sudhakar
In the Cloud computing platform, several technologies are practiced to manage the huge amount of information and also afford the comfort of routine. In this state, every cloud-based application plays an extensive role in the real-time applications. To avail efficient facilities to the patients, this paper presents an optimal feature selection based data classification model particularly for cloud platform. The presented model is based on two stages namely genetic algorithm based feature selection (GA-FS) and neural network (NN) based data classification. The presented GA-NN model is applied to diagnose the diseases and its various stages. The experimentations have been directed by the benchmark dataset and the real-time medicinal data that is gathered from numerous medical organizations. The simulation outcomes demonstrate that the efficiency of the GA-NN method beats the prevailing methods to predict diseases.
{"title":"An optimal feature selection based classification model for disease diagnosis in cloud environment","authors":"K. Veerasekaran, P. Sudhakar","doi":"10.1109/ICSSIT46314.2019.8987874","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987874","url":null,"abstract":"In the Cloud computing platform, several technologies are practiced to manage the huge amount of information and also afford the comfort of routine. In this state, every cloud-based application plays an extensive role in the real-time applications. To avail efficient facilities to the patients, this paper presents an optimal feature selection based data classification model particularly for cloud platform. The presented model is based on two stages namely genetic algorithm based feature selection (GA-FS) and neural network (NN) based data classification. The presented GA-NN model is applied to diagnose the diseases and its various stages. The experimentations have been directed by the benchmark dataset and the real-time medicinal data that is gathered from numerous medical organizations. The simulation outcomes demonstrate that the efficiency of the GA-NN method beats the prevailing methods to predict diseases.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115818299","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 : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987782
Narmatha Venugopal, Kamarasan Mari
Generally, identification of Glaucoma in color fundus images is a crucial process, which needs more knowledge and experience. An efficient spatial hashing-based data structure for facilitating the investigation of 3D shapes by the use of CNN. This model makes use of the sparse occupancy of 3D shape boundary and constructs the hierarchical hash tables for an input model under dissimilar resolutions. This paper designs an automated Glaucoma image classification model utilizing Perceptual Hash-Based Convolutional Neural Network (PH-CNN) model. The presented classification model operates in different stages namely feature extraction, feature reduction and classification. Initially, feature extraction process takes place via Discrete Wavelet Transform (DWT). Next, selection of features or reduction of features is carried out by the Principal Component Analysis (PCA) technique. Finally, PH-CNN model is applied for the classification of Glaucoma images. For validating the effective results of the presented PH-CNN approach, a benchmark dataset is applied and the results are assessed under several dimensions. These maximum values attained from the experimentation indicated that the projected model can be applied to diagnose the Glaucoma disease in real time.
{"title":"An Automated Glaucoma Image Classification model using Perceptual Hash-Based Convolutional Neural Network","authors":"Narmatha Venugopal, Kamarasan Mari","doi":"10.1109/ICSSIT46314.2019.8987782","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987782","url":null,"abstract":"Generally, identification of Glaucoma in color fundus images is a crucial process, which needs more knowledge and experience. An efficient spatial hashing-based data structure for facilitating the investigation of 3D shapes by the use of CNN. This model makes use of the sparse occupancy of 3D shape boundary and constructs the hierarchical hash tables for an input model under dissimilar resolutions. This paper designs an automated Glaucoma image classification model utilizing Perceptual Hash-Based Convolutional Neural Network (PH-CNN) model. The presented classification model operates in different stages namely feature extraction, feature reduction and classification. Initially, feature extraction process takes place via Discrete Wavelet Transform (DWT). Next, selection of features or reduction of features is carried out by the Principal Component Analysis (PCA) technique. Finally, PH-CNN model is applied for the classification of Glaucoma images. For validating the effective results of the presented PH-CNN approach, a benchmark dataset is applied and the results are assessed under several dimensions. These maximum values attained from the experimentation indicated that the projected model can be applied to diagnose the Glaucoma disease in real time.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132049905","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 : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987755
J. Sahu, S. Mishra, K. Hariharan
In the modern world with the advancement of technologies in solid-state electronics, the use of power electronics devices is playing a crucial role in the conversion and control of electric power. By using these innovative devices in 3-phase voltage source inverters, precise and smooth control over the conversion of electrical power can be achieved. But on the other hand, this leads to Total Harmonic Distortion (THD) leading to an adverse effect on the overall system performance. The optimization technique has emerged as a newly popular method for selective harmonic elimination. The main focus of this paper is on simulation study for harmonic analysis of 3-phase voltage source inverter by using particle swarm optimization (PSO) technique. By considering the expression of THD as an objective function, optimization is achieved in the PSO algorithm. This paper also discusses the harmonic analysis of the proposed inverter for conventional PWM techniques such as sinusoidal pulse width modulation (SPWM) and trapezoidal pulse width modulation (TPWM). The harmonic spectrum of the output voltage of the inverter is compared for SPWM, TPWM, and PSO by using MATLAB. From THD analysis, it is observed that PSO gives better performance than other conventional techniques.
{"title":"Harmonic Analysis of Three Phase Inverter by using Particle Swarm Optimization Technique","authors":"J. Sahu, S. Mishra, K. Hariharan","doi":"10.1109/ICSSIT46314.2019.8987755","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987755","url":null,"abstract":"In the modern world with the advancement of technologies in solid-state electronics, the use of power electronics devices is playing a crucial role in the conversion and control of electric power. By using these innovative devices in 3-phase voltage source inverters, precise and smooth control over the conversion of electrical power can be achieved. But on the other hand, this leads to Total Harmonic Distortion (THD) leading to an adverse effect on the overall system performance. The optimization technique has emerged as a newly popular method for selective harmonic elimination. The main focus of this paper is on simulation study for harmonic analysis of 3-phase voltage source inverter by using particle swarm optimization (PSO) technique. By considering the expression of THD as an objective function, optimization is achieved in the PSO algorithm. This paper also discusses the harmonic analysis of the proposed inverter for conventional PWM techniques such as sinusoidal pulse width modulation (SPWM) and trapezoidal pulse width modulation (TPWM). The harmonic spectrum of the output voltage of the inverter is compared for SPWM, TPWM, and PSO by using MATLAB. From THD analysis, it is observed that PSO gives better performance than other conventional techniques.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134104809","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 : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987929
M. Ananda, A. Kalpana
In present days the use of wireless communication devices are increasing drastically for communication, Because of huge wireless communication there is a chance of increase in noise level and less tuning range. At receivers even though Low noise Amplifier are used for removing noise in RF signal but after conversion into IF signal by Down conversion there exists noise, and also device should support wide tuning range. Hence RF Filters are required to reduce noise which are designed to operate on signal in MHz to GHz Frequency ranges proving wide Tuning range. This Frequency range is used by most Broadcast radio, TV, Wireless Communications and RF Filters will include some kind of filtering on the signals Transmitted or Received. In this Project an efficient RF Filter is designed at RF Frequency of 2.4GHz and the proposed RF Filter has a wide Tuning range of 122MHz and Low Power Consumption and used to reduce the noise levels in both Transmitter and Receiver.
{"title":"A Wide Tuning Range and Low Power RF Filter for Wireless Local Area Network Applications","authors":"M. Ananda, A. Kalpana","doi":"10.1109/ICSSIT46314.2019.8987929","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987929","url":null,"abstract":"In present days the use of wireless communication devices are increasing drastically for communication, Because of huge wireless communication there is a chance of increase in noise level and less tuning range. At receivers even though Low noise Amplifier are used for removing noise in RF signal but after conversion into IF signal by Down conversion there exists noise, and also device should support wide tuning range. Hence RF Filters are required to reduce noise which are designed to operate on signal in MHz to GHz Frequency ranges proving wide Tuning range. This Frequency range is used by most Broadcast radio, TV, Wireless Communications and RF Filters will include some kind of filtering on the signals Transmitted or Received. In this Project an efficient RF Filter is designed at RF Frequency of 2.4GHz and the proposed RF Filter has a wide Tuning range of 122MHz and Low Power Consumption and used to reduce the noise levels in both Transmitter and Receiver.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"24 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134183068","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 : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987849
Dharmendra Kumar, Saroj Hiranwal
Forest is considered as an important part in context to the environment. The major purpose is to inhale carbon dioxide and generate oxygen in their cycle of photosynthesis for maintaining a balance and healthy atmosphere. Examination of environmental disasters, such as biodiversity loss, deforestation, depletion of natural resources, etc., necessitates the computation of continuous change detection in the forest. Nowadays, land cover change analysis is performed using satellite images. Several techniques are introduced for forest change detection, but missing data in the satellite images is a serious problem due to artifacts, cloud occlusion, and so on. Thus, techniques handling missing data for forest change detection are essential. As a result, this survey provides a review of unique forest change detection mechanisms. Therefore, this paper presents a complete analysis of 25 papers presenting a forest change detection methods, like Machine learning techniques, Pixel-based techiques. In addition, a detailed investigation are carried out based on the performance measures, images adapted, datasets used, evaluation metrics, and accuracy range. Finally, the issues faced by different forest change detection methods are offered to extend the researchers to form enhanced role in considerable detection methods.
{"title":"Descriptive Study and Analysis of Forest Change detection techniques using Satellite Images","authors":"Dharmendra Kumar, Saroj Hiranwal","doi":"10.1109/ICSSIT46314.2019.8987849","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987849","url":null,"abstract":"Forest is considered as an important part in context to the environment. The major purpose is to inhale carbon dioxide and generate oxygen in their cycle of photosynthesis for maintaining a balance and healthy atmosphere. Examination of environmental disasters, such as biodiversity loss, deforestation, depletion of natural resources, etc., necessitates the computation of continuous change detection in the forest. Nowadays, land cover change analysis is performed using satellite images. Several techniques are introduced for forest change detection, but missing data in the satellite images is a serious problem due to artifacts, cloud occlusion, and so on. Thus, techniques handling missing data for forest change detection are essential. As a result, this survey provides a review of unique forest change detection mechanisms. Therefore, this paper presents a complete analysis of 25 papers presenting a forest change detection methods, like Machine learning techniques, Pixel-based techiques. In addition, a detailed investigation are carried out based on the performance measures, images adapted, datasets used, evaluation metrics, and accuracy range. Finally, the issues faced by different forest change detection methods are offered to extend the researchers to form enhanced role in considerable detection methods.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133398550","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 : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987820
A. Pani, N. Nayak
The grid incorporation of solar power production creates nonlinearity, instability and entails improper energy management, which is still a challenging situation while installing a large solar power plant. Thus prediction of solar power generation is highly essential in different time horizons for maintaining proper power adjustment techniques and management. In this work a smart and competent prediction model has been implemented on a real time photovoltaic power plant. The Extreme learning machine (ELM) which is a new prediction technique is applied in this work. The weights of ELM are selected randomly in general. The performance of the forecasting model also depends on proper weight selection. Thus a new optimization technique such as harmony search optimization is applied to select the optimized weights. The forecasting model is implemented on an historical data set of real time solar power plant whose geographical location is given in the last part of section-II. The ELM model is activated to mobilize the feed forward neural network, iteratively, to achieve better forecasting error in each step. ELM model and the Harmony Search optimized ELM model are simulated for error calculation and their results are compared in terms of different measuring indices and their forecasting errors are compared.
{"title":"Short Term Forecasting of Solar Power Using Harmony Search based Extreme Learning Machine","authors":"A. Pani, N. Nayak","doi":"10.1109/ICSSIT46314.2019.8987820","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987820","url":null,"abstract":"The grid incorporation of solar power production creates nonlinearity, instability and entails improper energy management, which is still a challenging situation while installing a large solar power plant. Thus prediction of solar power generation is highly essential in different time horizons for maintaining proper power adjustment techniques and management. In this work a smart and competent prediction model has been implemented on a real time photovoltaic power plant. The Extreme learning machine (ELM) which is a new prediction technique is applied in this work. The weights of ELM are selected randomly in general. The performance of the forecasting model also depends on proper weight selection. Thus a new optimization technique such as harmony search optimization is applied to select the optimized weights. The forecasting model is implemented on an historical data set of real time solar power plant whose geographical location is given in the last part of section-II. The ELM model is activated to mobilize the feed forward neural network, iteratively, to achieve better forecasting error in each step. ELM model and the Harmony Search optimized ELM model are simulated for error calculation and their results are compared in terms of different measuring indices and their forecasting errors are compared.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"36 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131677286","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：