2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)最新文献
It’s very difficult to say whether a product being designed will adhere to all the regulatory & compliance needs with just customer specifications alone. Sometimes to comply with the regulatory requirement, we may need to change the Product specification. In addition, Reliability specification & demonstration plans are not drawn early in the project cycle leading to program delays & challenges in the field. There are many standards, models which companies follow for the ease of designing a compliant product. Here, in this paper some of the major aspects which can be crucial are highlighted, in return help in getting a better product through “First Time Right” design principles, comprehensive compliance tests and application of comprehensive Reliability practices.
{"title":"Compliance: Conquer the rules for a better product","authors":"Amarja Mohan, Bandela Sujatha, Srividya Subbarao, Sumandra Ghosh Chowdhury","doi":"10.1109/TEMSMET51618.2020.9557499","DOIUrl":"https://doi.org/10.1109/TEMSMET51618.2020.9557499","url":null,"abstract":"It’s very difficult to say whether a product being designed will adhere to all the regulatory & compliance needs with just customer specifications alone. Sometimes to comply with the regulatory requirement, we may need to change the Product specification. In addition, Reliability specification & demonstration plans are not drawn early in the project cycle leading to program delays & challenges in the field. There are many standards, models which companies follow for the ease of designing a compliant product. Here, in this paper some of the major aspects which can be crucial are highlighted, in return help in getting a better product through “First Time Right” design principles, comprehensive compliance tests and application of comprehensive Reliability practices.","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116686950","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 : 2020-12-10DOI: 10.1109/TEMSMET51618.2020.9557401
Kedar Patel, Jaimin Shimpi, D. Kambaliya
The climate of planet earth has been observed to be affected by various radicals such as pollution of air, water, and ground. As a result, it has become important to analyze the undergoing changes and act upon accordingly. The climatic changes can depend upon a vast number of parameters whose data can be modelled and analyzed to derive many significant inferences and comparison. However, it has been believed that the climatic changes are linear and equally spread throughout the planet; hence to clear this misconception, our study presents an analytical study to determine the climatic variation taking place in two different places which are located in different geographic hemispheres, i.e. New York City and Sydney. The study conducts Multivariate Statistical Analysis of multiple parameters of climate changes and compares the same for both the cities. The study uses multiple tools and 3D mapping using R programming of more than 14,000 Data sets of the period 1982–2019, the has been fetched using NASA Power LARC data extraction of historical Climate parameters. The study also presents ANOVA tests and other quantitative comparisons while considering various data sizes. In the end, the study tries to derive conclusive results using multiple statistical inferences.
据观察，地球的气候受到各种极端因素的影响，如空气、水和地面的污染。因此，分析正在发生的变化并据此采取行动变得非常重要。气候变化可以依赖于大量的参数，这些参数的数据可以模拟和分析，从而得出许多重要的推论和比较。然而，人们一直认为气候变化是线性的，并且在整个地球上均匀分布;因此，为了消除这种误解，我们的研究提出了一项分析研究，以确定位于不同地理半球的两个不同地方(即纽约市和悉尼)发生的气候变化。该研究对气候变化的多个参数进行了多元统计分析，并对两个城市进行了比较。该研究使用了多种工具，并使用R编程对1982-2019年期间的14000多个数据集进行了3D映射，这些数据集是通过NASA Power LARC数据提取历史气候参数获得的。该研究还提出了方差分析测试和其他定量比较，同时考虑到不同的数据大小。最后，本研究试图通过多重统计推断得出结论性的结果。
{"title":"Multivariate Statistical Investigation of Climatic Changes for Northern & Southern Hemisphere","authors":"Kedar Patel, Jaimin Shimpi, D. Kambaliya","doi":"10.1109/TEMSMET51618.2020.9557401","DOIUrl":"https://doi.org/10.1109/TEMSMET51618.2020.9557401","url":null,"abstract":"The climate of planet earth has been observed to be affected by various radicals such as pollution of air, water, and ground. As a result, it has become important to analyze the undergoing changes and act upon accordingly. The climatic changes can depend upon a vast number of parameters whose data can be modelled and analyzed to derive many significant inferences and comparison. However, it has been believed that the climatic changes are linear and equally spread throughout the planet; hence to clear this misconception, our study presents an analytical study to determine the climatic variation taking place in two different places which are located in different geographic hemispheres, i.e. New York City and Sydney. The study conducts Multivariate Statistical Analysis of multiple parameters of climate changes and compares the same for both the cities. The study uses multiple tools and 3D mapping using R programming of more than 14,000 Data sets of the period 1982–2019, the has been fetched using NASA Power LARC data extraction of historical Climate parameters. The study also presents ANOVA tests and other quantitative comparisons while considering various data sizes. In the end, the study tries to derive conclusive results using multiple statistical inferences.","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125049147","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 : 2020-12-10DOI: 10.1109/TEMSMET51618.2020.9557365
Ujjwal, H. Singh, Neelam Verma
In order to improve and maintain the waste water quality where removal of nitrate and ammonium are stressed then some control techniques have been used. In this paper, a decentralized PI controller which is self-tuned is adaptable to change the controlled variable of the process for a multivariable system. This controller has been proposed with an adaptive interaction algorithm. The wastewater treatment plant is commonly known as complex and have large number of parameters and states. Also, some interaction methods named as Relative Gain Array (RGA) and Niederlinski Index (NI) have been used. These methods help to choose proper pairing so that not all output got effected. The aim of this paper is to tune the PI system parameters for controlling the concentration of the dissolve oxygen and nitrate with respect to a constant value.
{"title":"Self-tuning of Multivariable Plant","authors":"Ujjwal, H. Singh, Neelam Verma","doi":"10.1109/TEMSMET51618.2020.9557365","DOIUrl":"https://doi.org/10.1109/TEMSMET51618.2020.9557365","url":null,"abstract":"In order to improve and maintain the waste water quality where removal of nitrate and ammonium are stressed then some control techniques have been used. In this paper, a decentralized PI controller which is self-tuned is adaptable to change the controlled variable of the process for a multivariable system. This controller has been proposed with an adaptive interaction algorithm. The wastewater treatment plant is commonly known as complex and have large number of parameters and states. Also, some interaction methods named as Relative Gain Array (RGA) and Niederlinski Index (NI) have been used. These methods help to choose proper pairing so that not all output got effected. The aim of this paper is to tune the PI system parameters for controlling the concentration of the dissolve oxygen and nitrate with respect to a constant value.","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126997058","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 : 2020-12-10DOI: 10.1109/temsmet51618.2020.9557581
{"title":"[Copyright notice]","authors":"","doi":"10.1109/temsmet51618.2020.9557581","DOIUrl":"https://doi.org/10.1109/temsmet51618.2020.9557581","url":null,"abstract":"","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"333 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115966603","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 : 2020-12-10DOI: 10.1109/TEMSMET51618.2020.9557454
Harsh Dashora, J. Kumar, D. Mamatha
Designing of planar RF circuits needs an appropriate dielectric substrate to accommodate the required design in a specified area to exhibit required performance for intended application. Substrate plays an important role when it is employed at microwave and millimetre wave frequencies and good electrical as well as thermal stability is expected. The substrate parameter which may affect the overall RF circuit performance and those are very critical for selecting a substrate especially for space application is explained in this article.
{"title":"Effect of Dielectric Substrate and Substrate Selection at Microwave Frequencies","authors":"Harsh Dashora, J. Kumar, D. Mamatha","doi":"10.1109/TEMSMET51618.2020.9557454","DOIUrl":"https://doi.org/10.1109/TEMSMET51618.2020.9557454","url":null,"abstract":"Designing of planar RF circuits needs an appropriate dielectric substrate to accommodate the required design in a specified area to exhibit required performance for intended application. Substrate plays an important role when it is employed at microwave and millimetre wave frequencies and good electrical as well as thermal stability is expected. The substrate parameter which may affect the overall RF circuit performance and those are very critical for selecting a substrate especially for space application is explained in this article.","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131120462","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 : 2020-12-10DOI: 10.1109/TEMSMET51618.2020.9557402
Nasim Mia, Saikat Das, Moazzam Hossain, Nadim Ahmed
As energy demands are increasing exponentially due to the rapid growth in the world’s population as well as in economic and technological advancement, to meet the needs of an increasing energy-dependent society, the world needs to think about sustainable renewable sources. According to the World Energy Assessment, by the year 2050, the energy demand is expected to increase near 30TW [1]. Existing non-renewable sources, especially fossil fuels, are rarely sufficient to meet this enormous energy demand. The objective of this paper is to discuss why we should focus on renewable sources, its immense feasibility and how these sources, especially solar energy, will change the energy scenario in upcoming decades. In this paper, the whole work is divided into three sections. In the first section, the importance & the motivations behind concerning renewable energy is discussed. Furthermore, in the second and third sections, the present scenario of renewable energy as well as solar cell technology and a projection up to 2040–2050 along with scopes and challenges will be discussed respectively.
{"title":"A Review on Feasibility of Solar Based Renewable Energy: A Projection Up to 2050","authors":"Nasim Mia, Saikat Das, Moazzam Hossain, Nadim Ahmed","doi":"10.1109/TEMSMET51618.2020.9557402","DOIUrl":"https://doi.org/10.1109/TEMSMET51618.2020.9557402","url":null,"abstract":"As energy demands are increasing exponentially due to the rapid growth in the world’s population as well as in economic and technological advancement, to meet the needs of an increasing energy-dependent society, the world needs to think about sustainable renewable sources. According to the World Energy Assessment, by the year 2050, the energy demand is expected to increase near 30TW [1]. Existing non-renewable sources, especially fossil fuels, are rarely sufficient to meet this enormous energy demand. The objective of this paper is to discuss why we should focus on renewable sources, its immense feasibility and how these sources, especially solar energy, will change the energy scenario in upcoming decades. In this paper, the whole work is divided into three sections. In the first section, the importance & the motivations behind concerning renewable energy is discussed. Furthermore, in the second and third sections, the present scenario of renewable energy as well as solar cell technology and a projection up to 2040–2050 along with scopes and challenges will be discussed respectively.","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133512770","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 : 2020-12-10DOI: 10.1109/TEMSMET51618.2020.9557583
Rohan Wadhawan, Tanuj Drall, Shubham Singh, S. Chakraverty
Generative Adversarial Networks (GANs) have revolutionized image synthesis through many applications like face generation, photograph editing, and image super-resolution. Image synthesis using GANs has predominantly been uni-modal, with few approaches that can synthesize images from text or other data modes. Text-to-image synthesis, especially text-to-face synthesis, has promising use cases of robust face-generation from eye witness accounts and augmentation of the reading experience with visual cues. However, only a couple of datasets provide consolidated face data and textual descriptions for text-to-face synthesis. Moreover, these textual annotations are less extensive and descriptive, which reduces the diversity of faces generated from it. This paper empirically proves that increasing the number of facial attributes in each textual description helps GANs generate more diverse and real-looking faces. To prove this, we propose a new methodology that focuses on using structured textual descriptions. We also consolidate a Multi-Attributed and Structured Text-to-face (MAST) dataset consisting of high-quality images with structured textual annotations and make it available to researchers to experiment and build upon. Lastly, we report benchmark Fréchet’s Inception Distance (FID), Facial Semantic Similarity (FSS), and Facial Semantic Distance (FSD) scores for the MAST dataset.
{"title":"Multi-Attributed and Structured Text-to-Face Synthesis","authors":"Rohan Wadhawan, Tanuj Drall, Shubham Singh, S. Chakraverty","doi":"10.1109/TEMSMET51618.2020.9557583","DOIUrl":"https://doi.org/10.1109/TEMSMET51618.2020.9557583","url":null,"abstract":"Generative Adversarial Networks (GANs) have revolutionized image synthesis through many applications like face generation, photograph editing, and image super-resolution. Image synthesis using GANs has predominantly been uni-modal, with few approaches that can synthesize images from text or other data modes. Text-to-image synthesis, especially text-to-face synthesis, has promising use cases of robust face-generation from eye witness accounts and augmentation of the reading experience with visual cues. However, only a couple of datasets provide consolidated face data and textual descriptions for text-to-face synthesis. Moreover, these textual annotations are less extensive and descriptive, which reduces the diversity of faces generated from it. This paper empirically proves that increasing the number of facial attributes in each textual description helps GANs generate more diverse and real-looking faces. To prove this, we propose a new methodology that focuses on using structured textual descriptions. We also consolidate a Multi-Attributed and Structured Text-to-face (MAST) dataset consisting of high-quality images with structured textual annotations and make it available to researchers to experiment and build upon. Lastly, we report benchmark Fréchet’s Inception Distance (FID), Facial Semantic Similarity (FSS), and Facial Semantic Distance (FSD) scores for the MAST dataset.","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122019800","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 : 2020-12-10DOI: 10.1109/TEMSMET51618.2020.9557378
K. P. Suhaas, S. Senthil
The drastic increase in the difficulties for Quality of Service (QoS) centred infrastructure-less wireless communication and transmission classifications have strengthened the academicians and allied industries to advance further efficient and resourceful routing strategies to assist reliable and robust communication. Considering a large-scale and wide scenario of wireless networks, the zone based routing protocols consists of approaches that contain both the reactive and proactive network management approaches have remained and found substantial; but outdated direction-finding conclusions confines its usefulness for dynamic topology based interacting explanations such as Mobile Ad Hoc Networks (MANETs). MANET undergoes exceptionally high network and topologically varying conditions and the change necessitates ideal routing archetypal with augmented and increased network-awareness and multi-parameter aided approach to attain best possible QoS provision. With this as the consideration and motivation, in this paper, a Congestion Resilient Communication through Augmented Network-Aware and Multi-Parameter Assistance for Optimal Routing strategy has been technologically suggested with advanced and congestion resilient tactics for QoS assurance over the MANETs. Unlike traditional Zone Routing Protocol, the proposed Optimal Routing Decision model applies integrated and multiple parameters from various layers of the OSI layer to perform various procedures like Differentiation of Service (DoS), Dynamic Resource Scheduling (DRS), Dynamic Link and Packet Speed Approximation, Congestion Detection and Avoidance models. The multi-network parameters based best path detection and formation, enables the proposed strategy to exhibit 97.92% and 92% Packet Delivery Ratio for Real Time and Non-Real Time Data respectively, which is more than the existing approaches.
{"title":"A Robust Routing Strategy for Congestion Resilient Communication through Augmented Network-Aware and Multi-Parameter Assistance for Optimal Routing Decision in Zone Routing Protocol","authors":"K. P. Suhaas, S. Senthil","doi":"10.1109/TEMSMET51618.2020.9557378","DOIUrl":"https://doi.org/10.1109/TEMSMET51618.2020.9557378","url":null,"abstract":"The drastic increase in the difficulties for Quality of Service (QoS) centred infrastructure-less wireless communication and transmission classifications have strengthened the academicians and allied industries to advance further efficient and resourceful routing strategies to assist reliable and robust communication. Considering a large-scale and wide scenario of wireless networks, the zone based routing protocols consists of approaches that contain both the reactive and proactive network management approaches have remained and found substantial; but outdated direction-finding conclusions confines its usefulness for dynamic topology based interacting explanations such as Mobile Ad Hoc Networks (MANETs). MANET undergoes exceptionally high network and topologically varying conditions and the change necessitates ideal routing archetypal with augmented and increased network-awareness and multi-parameter aided approach to attain best possible QoS provision. With this as the consideration and motivation, in this paper, a Congestion Resilient Communication through Augmented Network-Aware and Multi-Parameter Assistance for Optimal Routing strategy has been technologically suggested with advanced and congestion resilient tactics for QoS assurance over the MANETs. Unlike traditional Zone Routing Protocol, the proposed Optimal Routing Decision model applies integrated and multiple parameters from various layers of the OSI layer to perform various procedures like Differentiation of Service (DoS), Dynamic Resource Scheduling (DRS), Dynamic Link and Packet Speed Approximation, Congestion Detection and Avoidance models. The multi-network parameters based best path detection and formation, enables the proposed strategy to exhibit 97.92% and 92% Packet Delivery Ratio for Real Time and Non-Real Time Data respectively, which is more than the existing approaches.","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131111360","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 : 2020-12-10DOI: 10.1109/TEMSMET51618.2020.9557432
S. Nandyal, Nikhil S Tengli
In recent days classification of images over fashion domain has become fundamental research problem with lot of computer vision based applications. In most of the existing research image classification is done based on the labels on the objects, however in the real world scenarios the images needs to classified into the labels based on the domain specific with proper guidelines, therefore the existing research works fails in achieving the evaluation measures like classification accuracy, precision, recall and time take taken for classification, Hence there is need of an efficient frameworks that classifies the images based on fashion and fabric by addressing existing research problems. This paper presents an efficient framework for segmenting using grab cut techniques with the integrating the histograms of oriented gradients (HOG) and the speeded-up robust features (SURF) techniques. Whereas HOG technique is used to retrieve the global features and SURF technique is used for the local features and then segmentation is done based on Scale-Invariant Feature Transform(SIFT) method that segments the line, solve the incident scaling, changes in lighting condition and rotation between the two images, Later classification of the clothing images is done by using feature matching classification techniques, with proper text analysis the classification of images is done based on color and fabric of the image. The proposed technique is compared with existing multi-level classification technique to prove the proposed framework is more efficient than existing works. With the proposed technique, we could able to achieve the accuracy of 93% by varying the dataset of the images which is 10–15% more accurate than existing multi-level classification.
{"title":"An efficient framework for classifying the Clothing items based on fashion and fabric of the images","authors":"S. Nandyal, Nikhil S Tengli","doi":"10.1109/TEMSMET51618.2020.9557432","DOIUrl":"https://doi.org/10.1109/TEMSMET51618.2020.9557432","url":null,"abstract":"In recent days classification of images over fashion domain has become fundamental research problem with lot of computer vision based applications. In most of the existing research image classification is done based on the labels on the objects, however in the real world scenarios the images needs to classified into the labels based on the domain specific with proper guidelines, therefore the existing research works fails in achieving the evaluation measures like classification accuracy, precision, recall and time take taken for classification, Hence there is need of an efficient frameworks that classifies the images based on fashion and fabric by addressing existing research problems. This paper presents an efficient framework for segmenting using grab cut techniques with the integrating the histograms of oriented gradients (HOG) and the speeded-up robust features (SURF) techniques. Whereas HOG technique is used to retrieve the global features and SURF technique is used for the local features and then segmentation is done based on Scale-Invariant Feature Transform(SIFT) method that segments the line, solve the incident scaling, changes in lighting condition and rotation between the two images, Later classification of the clothing images is done by using feature matching classification techniques, with proper text analysis the classification of images is done based on color and fabric of the image. The proposed technique is compared with existing multi-level classification technique to prove the proposed framework is more efficient than existing works. With the proposed technique, we could able to achieve the accuracy of 93% by varying the dataset of the images which is 10–15% more accurate than existing multi-level classification.","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128750299","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}
Forecasting is considered one of the most imperative and perplex proceedings in the present-day. Weather forecasting is a natural process which entails the prediction of the change in the atmospheric conditions with the passage of time. It has become a core area of studies and analysis for the scientist owing to the brusque forecasts and approaches of weather. Weather forecasting has always been a challenging task. In several cases, scientists and researchers had attempted in establishing a linear association between the input and targeted data of the weather. Since, weather is non-linear and dynamic in nature, the target has shifted to prediction of non-linear weather data. Though weather prediction is relatively a statistical measure and is automated, with the traditional tools, its result is rather uncertain and not always accurate. Due to its non-linearity and complex process, the best approach for resolving such problems is with the use of Artificial Neural Network (ANN). ANN simplify the weather predictions with its better efficiency, reliability and accuracy. The features of ANN are not just to analyse the past data but also to acquire future predictions rendering to be much ideal for weather forecasting. NN is rather a complicated network which are pliable and flexible in nature. It is autodidactic with its existing training data consequently forging a new smart pattern useful for predicting the weather. Survey of various techniques of NN for weather prediction is provided and it is observed that by simply increasing the number of hidden layers the trained NN can predict and classify the weather variables with minimal error. In this paper, predictive analysis algorithm is incorporated with back propagation network(BPN) to predict future weather by training the network. The technical milestone, where various researchers have acquired on this discipline has been reviewed and presented in these surveys.
{"title":"Artificial Neural Network for Weather Forecasting: A Review","authors":"Ushakiran Huiningsumbam, Anjali Jain, Neelam Verma","doi":"10.1109/TEMSMET51618.2020.9557491","DOIUrl":"https://doi.org/10.1109/TEMSMET51618.2020.9557491","url":null,"abstract":"Forecasting is considered one of the most imperative and perplex proceedings in the present-day. Weather forecasting is a natural process which entails the prediction of the change in the atmospheric conditions with the passage of time. It has become a core area of studies and analysis for the scientist owing to the brusque forecasts and approaches of weather. Weather forecasting has always been a challenging task. In several cases, scientists and researchers had attempted in establishing a linear association between the input and targeted data of the weather. Since, weather is non-linear and dynamic in nature, the target has shifted to prediction of non-linear weather data. Though weather prediction is relatively a statistical measure and is automated, with the traditional tools, its result is rather uncertain and not always accurate. Due to its non-linearity and complex process, the best approach for resolving such problems is with the use of Artificial Neural Network (ANN). ANN simplify the weather predictions with its better efficiency, reliability and accuracy. The features of ANN are not just to analyse the past data but also to acquire future predictions rendering to be much ideal for weather forecasting. NN is rather a complicated network which are pliable and flexible in nature. It is autodidactic with its existing training data consequently forging a new smart pattern useful for predicting the weather. Survey of various techniques of NN for weather prediction is provided and it is observed that by simply increasing the number of hidden layers the trained NN can predict and classify the weather variables with minimal error. In this paper, predictive analysis algorithm is incorporated with back propagation network(BPN) to predict future weather by training the network. The technical milestone, where various researchers have acquired on this discipline has been reviewed and presented in these surveys.","PeriodicalId":342852,"journal":{"name":"2020 IEEE International Conference on Technology, Engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129117361","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：